© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 10361
    Prev
    Next
    INDEX
    Explanations

    warp, class, squats

    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_13_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
    beza
    0.23
    鳖
    0.20
     zlep
    0.20
    蝴
    0.20
    鱉
    0.20
    オート
    0.19
    机票
    0.19
     selepas
    0.19
    椙
    0.19
     यूक
    0.18
    POSITIVE LOGITS
     P
    0.22
     اعتق
    0.22
     נ
    0.22
     Apple
    0.22
     n
    0.21
     Rachel
    0.21
     o
    0.20
    elde
    0.20
     an
    0.20
     Review
    0.20
    Activations Density 0.012%

    No Known Activations