© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 815
    Prev
    Next
    INDEX
    Explanations

    export statements in code

    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_39_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
    戻
    0.45
     ফিরে
    0.43
     retour
    0.42
     지구
    0.41
     jaanu
    0.41
     RETURNS
    0.41
     tilbake
    0.41
    َاب
    0.41
     RETURN
    0.40
    庁
    0.39
    POSITIVE LOGITS
    StatusCodes
    0.41
     physically
    0.40
    ObjectID
    0.39
     Dominicana
    0.37
    rachten
    0.36
    DesignTime
    0.36
     डो
    0.36
    HTMLElement
    0.35
     peel
    0.34
    RQ
    0.34
    Activations Density 0.003%

    No Known Activations