© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 145912
    Prev
    Next
    INDEX
    Explanations

    word endings

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_59_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
    ந்த
    0.66
    be
    0.46
    ytoin
    0.46
    なが
    0.44
    ake
    0.43
    icism
    0.40
    自
    0.39
    まる
    0.39
    теля
    0.38
    eris
    0.38
    POSITIVE LOGITS
    ethylene
    0.46
    urethane
    0.44
    vinyl
    0.44
    ليل
    0.44
    LOADING
    0.40
    بيض
    0.39
    ೆಯೇ
    0.36
    льника
    0.36
    ')}
    0.35
     Config
    0.34
    Activations Density 0.002%

    No Known Activations