© 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. 248336
    Prev
    Next
    INDEX
    Explanations

    domino

    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
     е
    0.52
     ma
    0.52
     ма
    0.47
     кон
    0.47
     Ma
    0.46
     ई
    0.45
    Ma
    0.43
     e
    0.43
     মা
    0.43
    ｅ
    0.43
    POSITIVE LOGITS
     dom
    0.47
     domino
    0.47
    Doming
    0.44
     lo
    0.41
     tantos
    0.39
    洪
    0.38
     forging
    0.37
     just
    0.37
     Magist
    0.37
     Domino
    0.37
    Activations Density 0.000%

    No Known Activations