© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 16322
    Prev
    Next
    INDEX
    Explanations

    calculation and extraction

    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_40_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
     Follow
    0.35
     FOLLOW
    0.35
     out
    0.34
    Follow
    0.34
     پیروی
    0.33
    かれる
    0.33
     따라
    0.33
     follow
    0.32
     følge
    0.32
    遵
    0.32
    POSITIVE LOGITS
     conspicuously
    0.32
     awarding
    0.29
     vulture
    0.29
     *}(
    0.28
     booth
    0.27
     holding
    0.27
    holds
    0.27
    lineContainer
    0.27
    getStatus
    0.27
     prominently
    0.27
    Activations Density 0.019%

    No Known Activations