© 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. 215751
    Prev
    Next
    INDEX
    Explanations

    TV display ON

    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
    Not in Any Lists

    No Comments

    Negative Logits
    א
    1.26
     (
    1.24
     I
    1.23
    (
    1.18
    1.09
     of
    1.05
     (\
    1.02
     $\
    1.00
     harb
    0.98
    เหมือน
    0.98
    POSITIVE LOGITS
    ну
    1.37
    са
    1.32
    om
    1.22
    ре
    1.20
    not
    1.17
    os
    1.16
    don
    1.16
    ್ಟ
    1.13
    on
    1.11
    ্স
    1.10
    Activations Density 0.003%

    No Known Activations