© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 6622
    Prev
    Next
    INDEX
    Explanations

    man / men / gentlemen

    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_39_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
    干扰
    0.42
    ាតុ
    0.42
    ान्स
    0.40
    interference
    0.39
    ᑉ
    0.39
     mère
    0.39
    母
    0.38
    mère
    0.38
    hamilan
    0.38
     беремен
    0.38
    POSITIVE LOGITS
     남자
    0.73
     gentlemen
    0.71
     men
    0.66
    男
    0.65
     manly
    0.63
    남자
    0.63
     gentleman
    0.62
     masculine
    0.62
     Gentleman
    0.61
     Männer
    0.61
    Activations Density 0.174%

    No Known Activations