© 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-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 83355
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ing
    1.74
     as
    1.73
    .
    1.73
    us
    1.71
    _
    1.57
    ,
    1.48
    ة
    1.44
    ;
    1.38
    th
    1.31
    ps
    1.27
    POSITIVE LOGITS
     مي‌
    1.73
    ו
    1.55
    лась
    1.47
    اك
    1.46
    <0x80>
    1.45
     جاي
    1.40
     براي
    1.37
    ায়
    1.36
    </strong>
    1.34
    ري
    1.34
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.