© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 15819
    Prev
    Next
    INDEX
    Explanations

    strings of characters that match the names of towns and people from the country Turkmenistan

    oai_token-act-pair · gemini-2.0-flash

    azerbaijan football

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    خفض
    -0.52
     \@
    -0.52
     kuin
    -0.49
    ऽ
    -0.49
     mücade
    -0.49
    を選択します
    -0.48
    انتهای
    -0.48
     moeili
    -0.48
     "$@"
    -0.48
     "¿
    -0.48
    POSITIVE LOGITS
     initComponents
    0.98
    devamını
    0.97
    Rüyada
    0.96
    LookAnd
    0.93
    Diwedd
    0.92
    脚注の使い方
    0.91
     transfieras
    0.91
     متعلقه
    0.90
     estekak
    0.89
    //
    0.88
    Activations Density 0.133%

    No Known Activations