© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179754
    Prev
    Next
    INDEX
    Explanations

    The letter Y

    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
    灌
    0.43
     ínt
    0.41
     ढ
    0.41
    abl
    0.40
     nCurrent
    0.39
    षे
    0.39
     Lien
    0.39
     vin
    0.38
     Isha
    0.38
     Schwe
    0.38
    POSITIVE LOGITS
     अम्
    0.45
    ឿង
    0.41
    윤
    0.41
    Campo
    0.40
    Yay
    0.39
    elda
    0.38
    ья
    0.38
    Yb
    0.38
    عکس
    0.38
    əd
    0.38
    Activations Density 0.001%

    No Known Activations