© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 44545
    Prev
    Next
    INDEX
    Explanations

    question words

    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_22_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
     ECS
    0.41
     aconteceu
    0.41
    ٽ
    0.41
     αλλά
    0.41
    特別
    0.39
     Antioxid
    0.39
    OWER
    0.38
     Grandes
    0.38
     venne
    0.38
     Özellikle
    0.38
    POSITIVE LOGITS
    graphHead
    0.42
    काब
    0.38
    >^
    0.38
     เรียก
    0.38
    閻
    0.38
    considered
    0.37
     ورح
    0.37
    ="#!"
    0.37
    president
    0.37
     सूचीबद्ध
    0.36
    Activations Density 0.003%

    No Known Activations