© 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. 109278
    Prev
    Next
    INDEX
    Explanations

    Land Acquisition

    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
    in
    1.09
    have
    1.09
    ۰
    1.00
    에
    0.98
    the
    0.97
    to
    0.96
    ار
    0.95
    do
    0.90
    cycling
    0.89
    re
    0.86
    POSITIVE LOGITS
    ت
    1.27
    H
    1.10
    т
    1.06
    M
    1.04
    ↵↵
    1.01
     Aquí
    0.90
    ক
    0.86
    ية
    0.86
     is
    0.85
     Então
    0.84
    Activations Density 0.001%

    No Known Activations