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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 7673
    Prev
    Next
    INDEX
    Explanations

    mentions of European aristocratic titles and place names

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_4/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
    <bos>
    -0.88
     Theſe
    -0.68
     ſur
    -0.67
     noqa
    -0.67
     Beſ
    -0.66
     abſ
    -0.65
    ſelf
    -0.61
     reaſon
    -0.61
     miſ
    -0.60
     tranſ
    -0.60
    POSITIVE LOGITS
     BitmapFactory
    0.68
    osph
    0.64
    VIAF
    0.59
    ngdoc
    0.55
    Collegamenti
    0.55
    ApiOperation
    0.55
     Cypri
    0.54
     Liban
    0.53
    ')}}
    0.51
    ))),
    0.50
    Activations Density 2.163%

    No Known Activations