© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 942
    Prev
    Next
    INDEX
    Explanations

    css class names

    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_38_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
     profesión
    0.43
    ര്‍ഷ
    0.39
    鲷
    0.39
     ontwikkel
    0.38
    argsort
    0.38
     medición
    0.38
     ontwikkeling
    0.38
    ညာ
    0.38
    ทยาลัย
    0.38
    嬙
    0.38
    POSITIVE LOGITS
     class
    0.78
    Class
    0.74
    class
    0.73
     класс
    0.71
     Class
    0.70
     classe
    0.68
    ActiveClass
    0.67
     Klasse
    0.67
     classes
    0.66
    クラス
    0.66
    Activations Density 0.018%

    No Known Activations