© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200732
    Prev
    Next
    INDEX
    Explanations

    *

    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_46_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
     looks
    0.42
     കാലാവ
    0.42
    अप्र
    0.42
     alguma
    0.40
    Задача
    0.40
    뽀
    0.39
     alguna
    0.39
     algún
    0.39
    looks
    0.39
    Looks
    0.39
    POSITIVE LOGITS
     health
    0.42
     pur
    0.40
    health
    0.39
    pur
    0.37
    健康
    0.37
     wellbeing
    0.37
    पुर
    0.35
    调整
    0.35
    矸
    0.35
    фор
    0.35
    Activations Density 0.003%

    No Known Activations