© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 13580
    Prev
    Next
    INDEX
    Explanations

    1

    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_15_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
     medi
    0.52
     சுண்ணாம்பு
    0.50
     উপজেলায়
    0.49
     विजे
    0.49
     unbe
    0.47
     noten
    0.47
    CreateIndex
    0.47
    ．
    0.47
    મ
    0.46
     तक
    0.46
    POSITIVE LOGITS
     Petrov
    0.54
    эф
    0.50
     Russian
    0.49
     Jiang
    0.49
    !'
    0.48
     Manor
    0.48
    p
    0.48
    !",
    0.48
     Фа
    0.48
     Rússia
    0.48
    Activations Density 0.001%

    No Known Activations