© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 30916
    Prev
    Next
    INDEX
    Explanations

    links and URLs

    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_31_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
    প্রাচ
    0.34
    ಷ್ಯ
    0.34
    எஸ்
    0.34
     ہے۔
    0.32
    SpawnEntry
    0.32
     Сури
    0.32
    맨
    0.31
     năm
    0.31
    사를
    0.31
     เฟ
    0.31
    POSITIVE LOGITS
    ák
    0.36
    ྵ
    0.35
    ويل
    0.34
     Unidas
    0.33
    oult
    0.33
    rum
    0.33
    ctuations
    0.33
    bindung
    0.33
     quelles
    0.33
    結合
    0.32
    Activations Density 0.842%

    No Known Activations