© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 205686
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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_10_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
     an
    0.82
     be
    0.82
     the
    0.75
     to
    0.67
    ก
    0.61
     a
    0.59
    iggers
    0.58
     our
    0.58
    ă
    0.57
     all
    0.56
    POSITIVE LOGITS
    他の
    0.54
     spineItem
    0.51
    ुष
    0.49
     dukkham
    0.49
    副作用
    0.49
     非
    0.48
    िफिशियल
    0.48
    見積
    0.48
    рија
    0.48
    ри
    0.48
    Activations Density 0.012%

    No Known Activations