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. 16291
    Prev
    Next
    INDEX
    Explanations

    text related to copyright and image use permissions from libraries and archives

    oai_token-act-pair · gemini-2.0-flash

    use

    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
    expandindo
    -0.94
    DockStyle
    -0.82
    DoubleQuotes
    -0.76
    </tfoot>
    -0.74
     ſta
    -0.69
     Theſe
    -0.68
    Personendaten
    -0.67
     ſtand
    -0.66
     raiſ
    -0.66
     newBuilder
    -0.66
    POSITIVE LOGITS
     use
    0.90
     usage
    0.67
     Use
    0.65
     uses
    0.64
    Use
    0.61
     utilise
    0.58
     sử
    0.57
     utilize
    0.57
     USE
    0.57
     utiliser
    0.56
    Activations Density 1.729%

    No Known Activations