© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 77471
    Prev
    Next
    INDEX
    Explanations

    concubine, seduction, powerful women

    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
    アナログ
    0.39
    wunsch
    0.38
    %、
    0.36
    dataTable
    0.36
    AutoScale
    0.35
    cityName
    0.35
    缄
    0.35
     dehuman
    0.34
     timeCounter
    0.34
    脊
    0.34
    POSITIVE LOGITS
     budget
    0.40
     consul
    0.40
    恋愛
    0.38
    γρά
    0.38
     queen
    0.38
     영향
    0.38
     선물
    0.38
    achet
    0.37
    の影響
    0.37
     affair
    0.37
    Activations Density 0.041%

    No Known Activations