© 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. 46632
    Prev
    Next
    INDEX
    Explanations

    place names

    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
    <
    0.68
    direito
    0.66
    V
    0.66
    grains
    0.64
    Hình
    0.64
    S
    0.61
    AR
    0.61
    전에
    0.60
    Vacuum
    0.60
    오늘
    0.59
    POSITIVE LOGITS
     preseason
    0.72
     国内
    0.71
     ﷺ
    0.69
     ชาว
    0.68
     cognit
    0.68
     gé
    0.66
     źród
    0.66
     デ
    0.66
     coexist
    0.65
     leech
    0.64
    Activations Density 0.003%

    No Known Activations