Greenwashing Language Detector

How Greenwashing Language Detector works

Press Load model once: your browser downloads Gemma 4 E2B instruction-tuned (web build) (2.0 GB) from this site and keeps it in its cache. Then add your text and press Classify locally. The model runs on this device using your graphics card, so nothing you enter is sent to a server. Until the model is loaded, or if your device cannot run it, the tool falls back to a simple keyword check and labels the result as the fallback.

Gemma 4 E2B instruction-tuned (web build) is a small open language model from Google. The tool sends it the instruction below plus your text, asks for a JSON answer with fixed fields, and shows each field as a card. It runs at temperature 0, so the same input gives the same answer on the same device, though different graphics cards can word it slightly differently.

Inputs longer than 6,000 characters are cut to that length before they reach the model, and the result says so. The model only sees what you paste: it does not look anything up.

The instruction the model gets

You review marketing copy for greenwashing language. Flag environmental words or phrases that are vague, absolute or unsupported (eco-friendly, green, natural, sustainable, planet-positive, carbon neutral, recyclable without detail), note any specific evidence the copy gives, and say what proof would make each claim checkable. Do not say whether the copy breaks any law and do not invent certifications.

What it returns

• Flagged wording: Each vague or unsupported phrase, quoted, with a short reason.
• Specific claims: Claims the copy backs with a figure, certification or scope, quoted.
• Proof that would help: For each flagged phrase, the evidence that would make it checkable.
• Plainer wording: A more specific version of the main claim, using only facts in the copy.

Worked example

The model's output for the built-in sample, recorded on a desktop browser. Your run may word things slightly differently.

Marketing claim: Our bottle is eco-friendly, planet-positive, guilt-free, and made with sustainable materials, but packaging does not list recycled content.

Flagged wording

eco-friendly planet-positive guilt-free sustainable materials

Specific claims

packaging does not list recycled content

Proof that would help

Definition of 'eco-friendly' and 'planet-positive' metrics Specific details on the 'sustainable materials' used Data or certification regarding the materials' environmental impact Specific evidence of recycled content in the packaging

Plainer wording

Our bottle is made with sustainable materials. Packaging does not list recycled content.

The model

The files are served from this site, versioned so a cached copy is never stale. Nothing is fetched from a third party while you use the tool.

Limitations

• Small language models make mistakes: they can miss an item, merge two, or state something more confidently than the text supports. Check the result against your input before you rely on it.
• It needs WebGPU and about 8 GB of memory, so it is offered on desktops and laptops, not on phones and tablets. Devices that cannot run it get the keyword fallback, clearly labelled.
• Results describe the input you gave, not the real-world situation behind it. Review them yourself before acting.

Good uses

• Triage climate and sustainability notes before deeper review
• Prepare consistent labels for repeat workflows
• Reduce manual sorting on small batches
• Keep sensitive drafts in the browser preview