© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 132778
    Prev
    Next
    INDEX
    Explanations

    <

    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_50_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
     생각해
    0.40
    ❞
    0.38
    xis
    0.37
     कीजिए
    0.37
     ।*
    0.37
    ㄵ
    0.36
    ”،
    0.36
     değildir
    0.35
     }-\
    0.34
    谦
    0.34
    POSITIVE LOGITS
    aboard
    0.42
     $('<
    0.40
    icist
    0.39
    Board
    0.37
     Vek
    0.37
    Div
    0.36
    CAPE
    0.36
    Og
    0.36
    erk
    0.36
     Opus
    0.36
    Activations Density 0.001%

    No Known Activations