© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 39951
    Prev
    Next
    INDEX
    Explanations

    King Kong, King Size, King's College London

    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_3_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    。
    0.69
    да
    0.68
     zaken
    0.67
     résoudre
    0.64
     répondre
    0.63
    ي
    0.62
     monetize
    0.62
     welcomed
    0.61
     proactively
    0.61
     laboratoire
    0.61
    POSITIVE LOGITS
    up
    0.92
    ون
    0.69
    set
    0.66
    fl
    0.64
    pent
    0.62
    wen
    0.61
    pel
    0.59
    q
    0.58
    फड
    0.58
    punk
    0.57
    Activations Density 0.002%

    No Known Activations