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. 16363
    Prev
    Next
    INDEX
    Explanations

    code or markup related to data processing

    oai_token-act-pair · gemini-2.0-flash

    code snippets

    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
    DoubleQuotes
    -0.69
    Portale
    -0.68
    DebuggerStep
    -0.60
    uxxxx
    -0.59
     ujednoznacz
    -0.59
     houſe
    -0.54
    nalité
    -0.53
     NSCoder
    -0.53
     column
    -0.51
     operator
    -0.51
    POSITIVE LOGITS
    ['
    1.00
    ["
    0.95
    [@"
    0.82
     ['
    0.71
     ["
    0.60
    "]["
    0.60
    ]['
    0.59
     Audiodateien
    0.57
    ('
    0.54
    ']['
    0.53
    Activations Density 1.833%

    No Known Activations