© 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. 25-GEMMASCOPE-2-TRANSCODER-262K
    7. 208859
    Prev
    Next
    INDEX
    Explanations

    determining biological sex/gender

    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_25_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
     meccan
    0.29
     arms
    0.29
     }$
    0.29
     bum
    0.27
    ，
    0.26
     comput
    0.26
    +'
    0.26
     ini
    0.25
    YAN
    0.25
     Arms
    0.25
    POSITIVE LOGITS
    horsepower
    0.30
     आणखी
    0.28
    ходы
    0.27
    篑
    0.26
    ]【
    0.26
     появления
    0.26
    히려
    0.26
     अत्यधिक
    0.25
    给大家
    0.25
     انتہائی
    0.25
    Activations Density 0.001%

    No Known Activations