© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13579
    Prev
    Next
    INDEX
    Explanations

    javascript code selectors

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
     jQuery
    1.60
     $.
    1.55
    $.
    1.37
    jQuery
    1.31
     jquery
    1.31
    jquery
    1.23
    .$.
    1.16
     $,
    0.97
    $(
    0.88
    $,
    0.84
    POSITIVE LOGITS
     তান
    0.40
    iet
    0.40
    zag
    0.40
     Rasmussen
    0.40
    คอน
    0.39
    Partners
    0.38
    COS
    0.38
    ocos
    0.38
    DockStyle
    0.37
    top
    0.37
    Activations Density 0.029%

    No Known Activations