© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 15092
    Prev
    Next
    INDEX
    Explanations

    numbers and code elements

    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_40_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
    flatten
    0.40
    一本
    0.38
    otted
    0.35
    Dense
    0.34
    ーストラリア
    0.34
    痢
    0.33
    cactus
    0.33
    inth
    0.32
    Refs
    0.32
    ceau
    0.31
    POSITIVE LOGITS
     ۹
    0.75
     ۶
    0.72
     ۵
    0.70
     ۱
    0.68
     ২
    0.66
     ৯
    0.66
     ۷
    0.66
     ११
    0.64
     २
    0.64
     ۸
    0.63
    Activations Density 0.459%

    No Known Activations