© 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. 36696
    Prev
    Next
    INDEX
    Explanations

    position, Existence, 傾向, 規模, schedule, 派, 格

    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
     a
    0.61
     season
    0.59
    プログラム
    0.55
     long
    0.53
    season
    0.53
     t
    0.52
     temporada
    0.52
     Ferrari
    0.52
     Season
    0.52
    </b>
    0.51
    POSITIVE LOGITS
    ٬
    0.57
    ியுள்ள
    0.54
    ен
    0.53
    <0x86>
    0.53
     möj
    0.53
    ف
    0.53
    é
    0.51
    AutoStabilise
    0.51
    ى
    0.50
    潁
    0.50
    Activations Density 0.008%

    No Known Activations