© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 80784
    Prev
    Next
    INDEX
    Explanations

    system design

    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_31_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
    ندي
    0.33
     grop
    0.33
    閂
    0.32
     струк
    0.32
     contracts
    0.32
    未必
    0.32
    谄
    0.32
     structuring
    0.31
    懵
    0.31
     nutshell
    0.31
    POSITIVE LOGITS
     System
    0.79
    System
    0.77
     sistem
    0.75
     sistema
    0.73
     system
    0.71
    system
    0.70
     SYSTEM
    0.70
    Sistema
    0.70
     Sistem
    0.70
    システム
    0.69
    Activations Density 0.004%

    No Known Activations