© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 52932
    Prev
    Next
    INDEX
    Explanations

    in the

    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_31_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
     ე
    0.35
    šit
    0.31
    coons
    0.31
    pios
    0.30
    erevan
    0.30
    ান্তরে
    0.30
    ѣ
    0.29
     ஈர
    0.29
    orems
    0.29
    preds
    0.29
    POSITIVE LOGITS
     gü
    0.28
     পা
    0.27
     Rm
    0.27
    Rm
    0.26
     상세보기
    0.25
     legenda
    0.25
     actionPerformed
    0.25
     Fault
    0.25
     ml
    0.25
    tableView
    0.25
    Activations Density 0.000%

    No Known Activations