© 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. 102937
    Prev
    Next
    INDEX
    Explanations

    стороны определенных групп

    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
    l
    1.27
    n
    1.25
    g
    1.16
    to
    1.13
    ست
    1.09
    ي
    1.05
    k
    1.04
    यों
    1.02
    ﻡ
    1.02
    m
    1.01
    POSITIVE LOGITS
     of
    1.11
     in
    1.02
    ные
    1.00
    .
    0.99
    ק
    0.96
    ના
    0.96
    CTION
    0.94
     are
    0.92
    op
    0.91
    력을
    0.89
    Activations Density 0.000%

    No Known Activations