© 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. 135357
    Prev
    Next
    INDEX
    Explanations

    affiliates

    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
    зм
    1.21
    6
    1.08
    ון
    1.03
     larval
    1.01
     rapides
    1.01
    の
    1.00
     satis
    0.96
     constructively
    0.95
    できる
    0.95
    ದಿ
    0.93
    POSITIVE LOGITS
    ines
    1.15
     and
    0.96
    ',
    0.94
    test
    0.94
    ter
    0.93
    ä
    0.92
    import
    0.90
     University
    0.89
    to
    0.89
    0.89
    Activations Density 0.001%

    No Known Activations