© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 6039
    Prev
    Next
    INDEX
    Explanations

    men or 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_40_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
    აზე
    0.37
     पढ़ा
    0.36
    textfield
    0.35
    ң
    0.35
     presets
    0.35
     JUL
    0.34
    FromBody
    0.34
    餅
    0.34
     plugins
    0.34
     predic
    0.34
    POSITIVE LOGITS
     women
    2.13
     womens
    2.05
     Women
    1.88
     Womens
    1.81
    Women
    1.79
     men
    1.76
     mens
    1.73
     WOMEN
    1.67
    メンズ
    1.63
    women
    1.63
    Activations Density 0.085%

    No Known Activations