© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10253
    Prev
    Next
    INDEX
    Explanations

    XML tags related to questions, responses, and categories

    oai_token-act-pair · gemini-2.0-flash

    va

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     prisonniers
    -0.55
    арт
    -0.54
    oga
    -0.51
     spalle
    -0.50
     pensées
    -0.50
     popoli
    -0.50
     Jerusalén
    -0.49
     storici
    -0.47
     språk
    -0.47
     PopupWindow
    -0.47
    POSITIVE LOGITS
    <bos>
    2.52
    begin
    0.80
    ThroughAttribute
    0.74
    ItemBackground
    0.72
    __'
    0.71
    ’
    0.69
    '
    0.69
     referenties
    0.69
     الرياضيه
    0.69
     Bourgoin
    0.68
    Activations Density 56.257%

    No Known Activations