© 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. 9-GEMMASCOPE-2-TRANSCODER-262K
    7. 199313
    Prev
    Next
    INDEX
    Explanations

    waiving requirements, fees, or rights

    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_9_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
    t
    0.89
    ?
    0.87
    ।
    0.77
     дет
    0.74
     challengers
    0.74
    rupted
    0.72
    stellungen
    0.70
     nourished
    0.70
     ত
    0.70
     것입니다
    0.68
    POSITIVE LOGITS
    ם
    1.31
    ور
    1.12
    un
    1.04
    TS
    1.02
    га
    1.01
    MN
    1.00
    ו
    0.99
    ا
    0.98
    anın
    0.95
    HA
    0.94
    Activations Density 0.008%

    No Known Activations