© 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. 129121
    Prev
    Next
    INDEX
    Explanations

    k, king

    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
    ā
    1.10
    יות
    1.09
    ید
    1.08
    اری
    1.08
     불구하고
    1.08
    ת
    1.05
     I
    1.01
    ่
    1.00
     ferroc
    0.99
    ни
    0.98
    POSITIVE LOGITS
    u
    0.95
    s
    0.93
    س
    0.90
    serve
    0.88
    зму
    0.88
    ato
    0.88
    rmt
    0.87
     будто
    0.87
    7
    0.87
    ों
    0.86
    Activations Density 0.000%

    No Known Activations