© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 178950
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise

    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_29_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
     sailboat
    0.41
     토
    0.37
     мыкты
    0.37
     caminar
    0.36
     अर्
    0.36
     製品
    0.35
     இல்லாமல்
    0.34
     আনুষ্ঠানিকভাবে
    0.34
    }{(
    0.34
     सशक्त
    0.34
    POSITIVE LOGITS
    cke
    0.41
    🦄
    0.39
    fehl
    0.38
    方針
    0.38
     entertainer
    0.38
     पूछा
    0.37
    pues
    0.37
     entertainers
    0.37
     Stability
    0.36
    igheten
    0.36
    Activations Density 0.003%

    No Known Activations