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. 23-GEMMASCOPE-TRANSCODER-16K
    4. 12231
    Prev
    Next
    INDEX
    Explanations

    articles and related words, often followed by nouns

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_23/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
    SourceChecksum
    -0.78
     nonatomic
    -0.74
    schild
    -0.69
    henswürdigkeiten
    -0.67
    Према
    -0.66
     Signalez
    -0.66
    <bos>
    -0.66
    Зноскі
    -0.65
    TestingModule
    -0.64
    المكان
    -0.63
    POSITIVE LOGITS
    %")
    0.55
    ']=
    0.51
    ')(
    0.51
    Carta
    0.51
    (')
    0.50
    %</
    0.49
    ')}}"
    0.47
    ')}}">
    0.46
     ')
    
    0.45
    }<\
    0.45
    Activations Density 4.975%

    No Known Activations