© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 58240
    Prev
    Next
    INDEX
    Explanations

    females

    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_59_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
    emento
    0.35
    汨
    0.33
    Id
    0.33
     IHDA
    0.33
    experts
    0.32
     দে
    0.32
     Id
    0.32
     گوئی
    0.32
    idelberg
    0.32
    ANCEL
    0.31
    POSITIVE LOGITS
     woman
    0.51
     دختر
    0.50
     mulher
    0.49
     vrouw
    0.49
     sœurs
    0.48
     girl
    0.48
     女
    0.47
     femme
    0.46
     granddaughter
    0.46
     lady
    0.46
    Activations Density 0.007%

    No Known Activations