© 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. 5-GEMMASCOPE-2-TRANSCODER-262K
    7. 209496
    Prev
    Next
    INDEX
    Explanations

    stu or Cos prefixes

    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_5_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
    W
    1.59
    ك
    1.45
    سك
    1.34
    H
    1.34
    V
    1.30
    M
    1.25
    Z
    1.24
    ת
    1.23
    J
    1.21
    S
    1.20
    POSITIVE LOGITS
    t
    1.08
    be
    0.97
    0.96
     is
    0.96
    .
    0.95
    ä
    0.93
    '
    0.92
     are
    0.86
    le
    0.85
    jär
    0.85
    Activations Density 0.000%

    No Known Activations