© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 35114
    Prev
    Next
    INDEX
    Explanations

    words starting with W or wu

    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_31_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
    bone
    0.40
    noff
    0.38
    جھ
    0.37
     bone
    0.37
     portability
    0.37
    osity
    0.36
     δο
    0.36
    =[];
    0.35
    Viva
    0.35
    矫
    0.35
    POSITIVE LOGITS
     Worm
    0.46
     Woodward
    0.43
    WOR
    0.41
    woocommerce
    0.41
     worms
    0.41
     Woo
    0.39
     woodworking
    0.39
    Woo
    0.38
     worm
    0.38
    raisal
    0.38
    Activations Density 0.028%

    No Known Activations