© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 91634
    Prev
    Next
    INDEX
    Explanations

    old way, world, ways, IntelliSense, textbooks, trading, rules, order

    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_11_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
     are
    0.57
    b
    0.54
     insightful
    0.47
    ‬
    0.47
     ause
    0.46
    याल
    0.46
    auge
    0.46
    噹
    0.45
     inov
    0.45
    inspiring
    0.45
    POSITIVE LOGITS
    ны
    0.55
    íj
    0.52
    Sobre
    0.52
     Спорт
    0.50
     ५
    0.49
    5
    0.49
    ız
    0.49
    یاں
    0.49
    Primer
    0.49
    बद्दल
    0.48
    Activations Density 0.004%

    No Known Activations