Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 21-GEMMASCOPE-TRANSCODER-16K
    4. 5924
    Prev
    Next
    INDEX
    Explanations

    words that have to do with pollution or vehicle emissions

    oai_token-act-pair · gemini-2.0-flash

    specialized terminology or proper nouns

    np_token-act-pair-logits · gpt-4o-mini

    from

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_21/width_16k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    QMetaType
    -0.67
    ConstraintMaker
    -0.57
     चीज़ों
    -0.57
    JspWriter
    -0.53
    tagHelperRunner
    -0.52
    WebVitals
    -0.51
    parsedMessage
    -0.51
     Cæsar
    -0.50
    FilterChain
    -0.50
    hoeddwyd
    -0.50
    POSITIVE LOGITS
    enumii
    0.64
    ætte
    0.60
    AnimationsModule
    0.60
    دانشنامهٔ
    0.58
    ondale
    0.57
    ագրություններ
    0.55
     saites
    0.52
    onshire
    0.52
     Sense
    0.51
    Étymologie
    0.50
    Activations Density 1.140%

    No Known Activations