© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2031
    Prev
    Next
    INDEX
    Explanations

    HTML table structure elements

    oai_token-act-pair · gemini-2.0-flash

    HTML table elements and attributes

    np_token-act-pair-logits · gpt-4o-mini

    HTML tables

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ScopeManager
    -0.51
    reactstrap
    -0.50
    migrationBuilder
    -0.46
     turno
    -0.46
    velocityY
    -0.45
     NUKAT
    -0.43
    del
    -0.42
     famí
    -0.41
     defaultstate
    -0.41
     ISNI
    -0.41
    POSITIVE LOGITS
     متعلقه
    0.64
    ViewFeatures
    0.63
     Efq
    0.61
    sunter
    0.59
    .)}
    0.59
     CHtml
    0.58
     مرئيه
    0.57
    webElementGuid
    0.57
    ).}
    0.57
    `).
    0.57
    Activations Density 0.070%

    No Known Activations