© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 14504
    Prev
    Next
    INDEX
    Explanations

    women and attractive men

    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_34_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
    ໍ
    0.40
     shove
    0.40
     отправ
    0.39
    ौती
    0.38
    ܝܢ
    0.38
    侕
    0.38
    ร้อง
    0.38
    🖉
    0.37
    ulis
    0.37
     دعوت
    0.37
    POSITIVE LOGITS
     महिले
    0.42
     muškar
    0.42
    luc
    0.39
    Handsome
    0.39
     girl
    0.38
    掴
    0.38
     handsome
    0.37
     мъ
    0.37
    girl
    0.37
     attractive
    0.36
    Activations Density 0.087%

    No Known Activations