© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 223636
    Prev
    Next
    INDEX
    Explanations

    pocket universes, dimensions, and monsters

    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
    ार
    0.66
    น
    0.63
    Ни
    0.59
    ナ
    0.55
    ла
    0.55
    та
    0.54
    रो
    0.54
    лыгы
    0.54
    ν
    0.54
    ро
    0.53
    POSITIVE LOGITS
     pocket
    0.89
     Pocket
    0.82
    pocket
    0.78
    Pocket
    0.73
     bolsillo
    0.64
     pockets
    0.57
     of
    0.55
     Inst
    0.53
     RSVP
    0.53
     जेब
    0.53
    Activations Density 0.007%

    No Known Activations