© 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. 135422
    Prev
    Next
    INDEX
    Explanations

    properties

    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
     \
    1.35
     be
    1.33
    ج
    1.27
     (
    1.26
    ع
    1.23
    ق
    1.16
     t
    1.14
     {
    1.12
     =
    1.07
    е
    1.04
    POSITIVE LOGITS
    ла
    1.17
    다
    1.09
    ।
    1.01
    ↵
    1.00
    kách
    1.00
    larni
    0.99
    ,
    0.99
    dons
    0.98
    ificaciones
    0.96
    ků
    0.95
    Activations Density 0.001%

    No Known Activations