© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35805
    Prev
    Next
    INDEX
    Explanations

    comma

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
    Ago
    0.44
     ent
    0.43
    茵
    0.43
    तियों
    0.43
     مذ
    0.40
    Рабо
    0.39
     अहम
    0.38
     Сегодня
    0.38
     ฉ
    0.38
    ិច្
    0.38
    POSITIVE LOGITS
    Non
    0.59
     Non
    0.57
    non
    0.54
     non
    0.50
    NON
    0.48
     غير
    0.44
     NON
    0.43
    非
    0.41
    ionar
    0.41
     Blanch
    0.38
    Activations Density 0.000%

    No Known Activations