© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 66895
    Prev
    Next
    INDEX
    Explanations

    gender

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
    統計
    0.46
     statistical
    0.41
    统计
    0.40
    statistical
    0.39
     اجيب
    0.39
    踩
    0.38
    stat
    0.38
    single
    0.38
    単
    0.38
    <'
    0.37
    POSITIVE LOGITS
     gender
    0.47
     Gender
    0.46
    faulse
    0.45
     genders
    0.44
    Gender
    0.44
     occupying
    0.43
     Tó
    0.42
     geslacht
    0.41
     sexu
    0.41
    gender
    0.39
    Activations Density 0.001%

    No Known Activations