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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16304
    Prev
    Next
    INDEX
    Explanations

    people's names and titles

    oai_token-act-pair · gemini-2.0-flash

    academic/professional titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope/layer_20/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
     فريبيس
    -0.92
    RenderAtEndOf
    -0.81
     незавершена
    -0.75
     Commencez
    -0.71
     Италијани
    -0.71
    WithIOException
    -0.71
     betweenstory
    -0.68
     initComponents
    -0.68
     referenties
    -0.67
    Дереккөздер
    -0.66
    POSITIVE LOGITS
     QC
    0.69
     CM
    0.69
     LC
    0.66
     M
    0.65
     SC
    0.65
     MC
    0.63
     CSC
    0.62
     BSC
    0.60
     MS
    0.60
     BS
    0.59
    Activations Density 0.603%

    No Known Activations