© 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. 75736
    Prev
    Next
    INDEX
    Explanations

    pandas cumulative sum

    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
    昶
    0.37
    hensible
    0.37
    Retour
    0.36
    ถี่
    0.35
    current
    0.35
     Outs
    0.35
    values
    0.34
     etapas
    0.34
    sell
    0.34
     étapes
    0.34
    POSITIVE LOGITS
     Tsuen
    0.48
    ➴
    0.46
     الزاويه
    0.43
     کیشن
    0.41
     quadrilateral
    0.40
     اربعه
    0.40
    菱
    0.39
     pushedAt
    0.39
     ਖ
    0.38
     제한
    0.38
    Activations Density 0.005%

    No Known Activations