© 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. 121662
    Prev
    Next
    INDEX
    Explanations

    bu, bus, busi, buzd

    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
    ر
    0.86
    ha
    0.74
    us
    0.73
     Конгрегация
    0.69
    StatusCode
    0.65
    t
    0.65
     União
    0.65
    IX
    0.64
    usel
    0.64
    cou
    0.63
    POSITIVE LOGITS
    '
    0.90
     baş
    0.75
     geçen
    0.75
    لی
    0.73
     değiş
    0.73
     utterly
    0.71
     הק
    0.71
     rp
    0.71
    این
    0.69
     အ
    0.68
    Activations Density 0.007%

    No Known Activations