© 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. 10251
    Prev
    Next
    INDEX
    Explanations

    Brockton Point Totem Poles

    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
     Elisa
    0.48
     "$(
    0.48
     onChanged
    0.48
     Hoop
    0.47
     HashTable
    0.46
    癀
    0.46
     CYAN
    0.46
     Greco
    0.45
     چاندی
    0.45
     रूई
    0.45
    POSITIVE LOGITS
    amed
    0.50
    igor
    0.50
    unjungi
    0.47
     D
    0.47
    wart
    0.46
    %
    0.46
    aways
    0.45
    unted
    0.45
     but
    0.44
    այր
    0.44
    Activations Density 0.001%

    No Known Activations