© 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. 129113
    Prev
    Next
    INDEX
    Explanations

    форматов

    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
    '
    1.93
     for
    1.39
     be
    1.33
    s
    1.28
    for
    1.21
     (
    1.18
     A
    1.16
    ד
    1.13
    (
    1.11
     S
    1.09
    POSITIVE LOGITS
    ır
    1.02
    办法
    0.98
    我
    0.96
    ంబేద్కర్
    0.96
     synergies
    0.95
    ール
    0.94
     марке
    0.94
     شفاف
    0.94
    จะ
    0.93
     contextos
    0.93
    Activations Density 0.000%

    No Known Activations