© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 102885
    Prev
    Next
    INDEX
    Explanations

    q sound marker

    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_1_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
    '
    1.16
     I
    0.93
    ئی
    0.91
     UNF
    0.88
     Scientology
    0.88
     COMEN
    0.88
     Ï
    0.88
    दीप
    0.87
     bellows
    0.84
    眞
    0.84
    POSITIVE LOGITS
    m
    1.45
    م
    1.45
    ن
    1.42
    n
    1.40
    н
    1.16
    ت
    1.14
    नं
    1.13
    re
    1.11
    at
    1.09
    ون
    1.07
    Activations Density 0.000%

    No Known Activations