© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 210635
    Prev
    Next
    INDEX
    Explanations

    broad, wide, широ

    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_10_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
    RE
    0.87
    Additional
    0.84
    '
    0.80
    ca
    0.75
    cn
    0.73
    Inform
    0.73
    cA
    0.73
    Ö
    0.73
    ging
    0.72
    c
    0.72
    POSITIVE LOGITS
    с
    0.91
     thereto
    0.72
     playback
    0.72
    ار
    0.71
    us
    0.71
    arasi
    0.70
    in
    0.68
    uis
    0.67
     boarded
    0.67
    νει
    0.66
    Activations Density 0.001%

    No Known Activations