© 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. 25648
    Prev
    Next
    INDEX
    Explanations

    picks"Hax"

    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
    с
    0.24
    س
    0.24
    v
    0.23
    é
    0.22
    ون
    0.21
    ار
    0.20
    la
    0.20
    л
    0.19
     ऐसी
    0.18
     डेटा
    0.18
    POSITIVE LOGITS
     be
    0.22
     not
    0.21
    on
    0.20
     beerCount
    0.19
     prosciutto
    0.19
     sheen
    0.18
     comportamenti
    0.18
     dee
    0.18
     brisket
    0.18
     dommages
    0.18
    Activations Density 0.002%

    No Known Activations