© 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. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 59389
    Prev
    Next
    INDEX
    Explanations

    say "y" prefix

    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
    љу
    0.43
    ُول
    0.40
    डक्शन
    0.40
    鈷
    0.40
    崠
    0.39
     الأن
    0.39
    ოვ
    0.38
    辐
    0.38
    erler
    0.37
    㖵
    0.37
    POSITIVE LOGITS
    yd
    1.01
    ys
    0.90
    yt
    0.88
    yn
    0.86
    yg
    0.85
    yb
    0.84
    yr
    0.76
    YN
    0.75
    yti
    0.73
    ysin
    0.73
    Activations Density 0.004%

    No Known Activations