© 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. 109461
    Prev
    Next
    INDEX
    Explanations

    RT and RTX abbreviations

    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
     உண்மையில்
    1.10
    ступ
    1.03
    の問題
    0.96
    স
    0.96
    ぁ
    0.95
     хотела
    0.94
    "</
    0.92
    $,
    0.90
    с
    0.90
    踏
    0.89
    POSITIVE LOGITS
    p
    1.43
    is
    1.34
    il
    1.29
    i
    1.27
    de
    1.23
    io
    1.21
    l
    1.21
    ла
    1.20
    el
    1.18
    iy
    1.16
    Activations Density 0.002%

    No Known Activations