© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 121022
    Prev
    Next
    INDEX
    Explanations

    playlist?list=PLZHQObOWTQDPD3MizzM2xVFitgF

    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_27_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
    （
    0.38
     вариант
    0.38
     sore
    0.37
     चार
    0.35
     জার
    0.34
     совершенно
    0.33
     অ্য
    0.33
    ках
    0.33
     время
    0.33
     версия
    0.33
    POSITIVE LOGITS
    iedenis
    0.39
    旨在
    0.38
     ded
    0.37
     proff
    0.37
     ሞ
    0.36
    🍳
    0.36
     redd
    0.34
     économ
    0.34
     scaffolding
    0.34
     săn
    0.33
    Activations Density 0.001%

    No Known Activations