© 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. 46598
    Prev
    Next
    INDEX
    Explanations

    equally unacceptable, time-consuming, unsettling, impressive, interesting, complex, important, finicky

    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
    é
    0.93
    ار
    0.91
    v
    0.85
    ků
    0.84
    í
    0.84
    an
    0.78
    in
    0.72
    х
    0.70
     necesitar
    0.70
    mile
    0.68
    POSITIVE LOGITS
    ม
    0.79
    .
    0.72
    \}.
    0.70
    BleStatus
    0.68
     Queste
    0.68
    .}$
    0.67
     〢
    0.64
    ๔
    0.64
     menyel
    0.64
    ну
    0.63
    Activations Density 0.001%

    No Known Activations