© 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. 14703
    Prev
    Next
    INDEX
    Explanations

    concept and related suffixes

    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
    ErrorBoundary
    0.45
    étrica
    0.42
    Buck
    0.42
     coco
    0.39
     Lug
    0.39
     acord
    0.38
    लावा
    0.38
    汙
    0.38
     appreciate
    0.37
    iece
    0.37
    POSITIVE LOGITS
    ual
    1.29
    ually
    1.27
    ualmente
    1.07
    UAL
    1.06
    uality
    0.95
    uali
    0.93
    uelle
    0.85
    uale
    0.82
    uales
    0.82
    uals
    0.81
    Activations Density 0.204%

    No Known Activations