© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127829
    Prev
    Next
    INDEX
    Explanations

    factor, Ativan, Sims, Temple

    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_3_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
     that
    0.68
     for
    0.63
    ار
    0.55
    ند
    0.55
     milliam
    0.55
    0.52
     I
    0.51
    uksen
    0.50
    t
    0.49
     pulang
    0.48
    POSITIVE LOGITS
    in
    1.04
    ो
    0.66
    ка
    0.60
    excludes
    0.60
    াই
    0.59
    expenses
    0.59
    ద్ధ
    0.59
     zwią
    0.59
     پوچھ
    0.57
    станции
    0.57
    Activations Density 0.000%

    No Known Activations