© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 2408
    Prev
    Next
    INDEX
    Explanations

    text prompts

    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
    ıştır
    0.33
    injlim
    0.32
     isometry
    0.31
    URNS
    0.30
    カイブ
    0.29
     movieId
    0.29
     프로그램
    0.29
     '$(
    0.29
    PROGRAM
    0.29
     programmatic
    0.29
    POSITIVE LOGITS
    Pere
    0.34
     Sakura
    0.30
     Pere
    0.29
    eple
    0.29
     Eureka
    0.29
    Lex
    0.29
    сні
    0.29
    Singapore
    0.29
     twists
    0.28
    Eureka
    0.28
    Activations Density 0.023%

    No Known Activations