© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 31629
    Prev
    Next
    INDEX
    Explanations

    brand 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_31_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
     covariate
    0.40
    писки
    0.40
    胚
    0.40
     turpis
    0.39
    ーストラリア
    0.39
    掲
    0.39
    ULTURAL
    0.38
    WeekDates
    0.38
    ધા
    0.37
    杵
    0.37
    POSITIVE LOGITS
     brands
    0.70
    品牌
    0.66
     브랜드
    0.66
     brand
    0.65
    brand
    0.65
    brands
    0.63
     Brand
    0.62
    Brand
    0.62
    品牌的
    0.62
    Brands
    0.61
    Activations Density 0.005%

    No Known Activations