© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217081
    Prev
    Next
    INDEX
    Explanations

    wand

    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_50_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
     ಧ
    0.40
    鍏
    0.39
    hbox
    0.38
    ্ত
    0.37
    カー
    0.37
    PINK
    0.36
    ớt
    0.35
    諄
    0.35
     extern
    0.35
    வேறு
    0.35
    POSITIVE LOGITS
     Wand
    2.02
    wand
    1.90
     wand
    1.88
    vand
    1.31
     wander
    1.30
     wandering
    1.27
     wandered
    1.27
     Wander
    1.17
     Wanda
    1.16
     wanders
    1.12
    Activations Density 0.004%

    No Known Activations