© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 36002
    Prev
    Next
    INDEX
    Explanations

    chip away at

    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_11_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
     갔
    0.63
     thiết
    0.58
    MCs
    0.58
    бки
    0.55
    镗
    0.54
    ckel
    0.53
    х
    0.53
    смотре
    0.53
    зии
    0.53
    acht
    0.52
    POSITIVE LOGITS
    a
    0.71
    AN
    0.71
    P
    0.65
    <0x0D>
    0.63
    R
    0.63
    en
    0.61
     ",
    0.61
    </h1>
    0.61
    in
    0.60
     INDIRECT
    0.59
    Activations Density 0.002%

    No Known Activations