© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 177122
    Prev
    Next
    INDEX
    Explanations

    say "W" words

    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
     Bho
    0.38
    neos
    0.36
     Stevie
    0.34
    stm
    0.33
     przyn
    0.33
    虏
    0.33
     ئە
    0.32
     ограничи
    0.32
    劧
    0.32
     tm
    0.32
    POSITIVE LOGITS
    ウェ
    1.49
    wel
    1.42
    WEL
    1.38
    웰
    1.38
    Wel
    1.36
    Wells
    1.30
     wel
    1.28
     Wells
    1.28
     Wel
    1.27
     Welles
    1.23
    Activations Density 0.001%

    No Known Activations