© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 42944
    Prev
    Next
    INDEX
    Explanations

    repasting, rephasing, repainting, reflows, repast

    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_3_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
    0.94
    í
    0.70
    z
    0.67
    á
    0.66
    เป็น
    0.63
    א
    0.61
    ai
    0.60
     sano
    0.59
    with
    0.58
     glimpses
    0.57
    POSITIVE LOGITS
    o
    0.76
    고
    0.71
    هما
    0.64
    oł
    0.61
    됐
    0.61
    ент
    0.59
    >
    0.59
    تان
    0.59
    നാള
    0.59
    ক্রিয়
    0.59
    Activations Density 0.019%

    No Known Activations