© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78303
    Prev
    Next
    INDEX
    Explanations

    Pax with following words

    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_0_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
    s
    2.36
    to
    2.06
    t
    2.00
    sp
    1.93
    1
    1.91
    sa
    1.79
    at
    1.76
    b
    1.73
    sm
    1.72
    sal
    1.67
    POSITIVE LOGITS
    ك
    2.06
    ن
    1.82
    ン
    1.78
     FISA
    1.49
    ق
    1.45
     дві
    1.40
    内容は
    1.35
    놁
    1.31
    無い
    1.27
    การ
    1.27
    Activations Density 0.000%

    No Known Activations