© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2279
    Prev
    Next
    INDEX
    Explanations

    references to television programs, especially talent shows

    oai_token-act-pair · gemini-2.0-flash

    Factor Nation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    greenrobot
    -0.62
    jspx
    -0.61
    clearpage
    -0.60
    <bos>
    -0.57
    SourceChecksum
    -0.57
    udy
    -0.56
    Przypisy
    -0.56
    minecraftforge
    -0.54
    zło
    -0.53
    Bibliografia
    -0.51
    POSITIVE LOGITS
     autorytatywna
    0.62
    kloped
    0.59
     تضيفلها
    0.55
    politan
    0.53
    parsedMessage
    0.47
     Reun
    0.45
     leetcode
    0.45
    MLLoader
    0.44
    hysema
    0.44
    മ്പ
    0.43
    Activations Density 2.299%

    No Known Activations