© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 23708
    Prev
    Next
    INDEX
    Explanations

    slice or piece

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_56_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
    卡
    2.14
     card
    1.93
    卡的
    1.79
    Card
    1.72
     Card
    1.72
     卡
    1.70
    card
    1.67
     कार्ड
    1.67
    カード
    1.66
     카드
    1.66
    POSITIVE LOGITS
    片
    0.44
     slice
    0.43
     片
    0.42
     piece
    0.39
     Slice
    0.38
     CPD
    0.37
     mảnh
    0.37
     Erik
    0.36
     insightful
    0.36
     rãi
    0.35
    Activations Density 0.003%

    No Known Activations