© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 225289
    Prev
    Next
    INDEX
    Explanations

    Arthur + Name

    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_10_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
    ())
    0.77
     ";
    0.75
    ↵
    0.75
    )(
    0.75
     They
    0.73
    irt
    0.70
    к
    0.70
     .
    0.68
    ك
    0.68
    ird
    0.67
    POSITIVE LOGITS
    ી
    0.86
    Nếu
    0.84
     bituminous
    0.84
     reinvent
    0.80
     करेगा
    0.80
    ত
    0.78
     collide
    0.77
    り
    0.77
     nourish
    0.77
     storey
    0.76
    Activations Density 0.001%

    No Known Activations