© 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. 207572
    Prev
    Next
    INDEX
    Explanations

    card

    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
     片
    0.44
     piece
    0.42
    片
    0.42
     CPD
    0.40
     Piece
    0.37
     mảnh
    0.37
     ус
    0.37
     Erik
    0.37
     slice
    0.37
    itioner
    0.36
    POSITIVE LOGITS
    卡
    2.19
     card
    1.97
    卡的
    1.80
    Card
    1.76
     Card
    1.73
     卡
    1.73
    カード
    1.72
    card
    1.71
     कार्ड
    1.70
     카드
    1.69
    Activations Density 0.005%

    No Known Activations