© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 13409
    Prev
    Next
    INDEX
    Explanations

    man, woman, girl, hombre, mujer

    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
    mrow
    0.39
     hoi
    0.37
    arlings
    0.37
    (&:
    0.36
     വിശ
    0.35
     Denim
    0.35
     ん
    0.35
    一位
    0.35
     Childhood
    0.35
    她们
    0.35
    POSITIVE LOGITS
     woman
    1.60
     uomo
    1.25
     женщина
    1.25
     мужчина
    1.23
     الرجل
    1.20
     girl
    1.20
     hombre
    1.20
     womans
    1.16
     mujer
    1.14
     man
    1.13
    Activations Density 0.062%

    No Known Activations