© 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. 22-GEMMASCOPE-2-TRANSCODER-262K
    7. 41959
    Prev
    Next
    INDEX
    Explanations

    snow and rain

    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_22_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
     redist
    0.18
     सूचीबद्ध
    0.17
    軼
    0.17
    ЕЛ
    0.17
    合适
    0.17
    ோம்
    0.16
    烷
    0.16
    '
    0.16
    ំណ
    0.16
     অনুম
    0.16
    POSITIVE LOGITS
    vaegir
    0.17
     тобі
    0.17
     foes
    0.17
     тебе
    0.16
    achsen
    0.16
    Callories
    0.16
     ரொ
    0.16
     पैदा
    0.16
     тебя
    0.16
    default
    0.16
    Activations Density 0.002%

    No Known Activations