© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90331
    Prev
    Next
    INDEX
    Explanations

    form of

    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_11_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
     Gallows
    0.69
    3
    0.68
     McDonalds
    0.64
     Fonda
    0.62
    ش
    0.61
    сл
    0.58
     Stove
    0.57
    9
    0.57
     Military
    0.57
    ла
    0.56
    POSITIVE LOGITS
    \
    0.73
     시
    0.57
    ,"
    0.55
     드
    0.55
     attrition
    0.55
    ,\"
    0.54
     immobilization
    0.54
    ī
    0.54
    ug
    0.54
     آئینہ
    0.52
    Activations Density 0.003%

    No Known Activations