© 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. 7-GEMMASCOPE-2-TRANSCODER-262K
    7. 34318
    Prev
    Next
    INDEX
    Explanations

    numbing sensation

    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_7_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
    1
    1.12
    ون
    1.00
     Į
    0.98
    ut
    0.86
    re
    0.85
    ir
    0.85
    ট
    0.84
    হ
    0.83
    ”),
    0.80
    ра
    0.80
    POSITIVE LOGITS
    (
    1.13
     be
    0.95
    \
    0.93
    ção
    0.92
    {
    0.92
    지고
    0.89
    .
    0.88
    \,
    0.85
     at
    0.83
     άλλα
    0.79
    Activations Density 0.001%

    No Known Activations