© 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. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 78428
    Prev
    Next
    INDEX
    Explanations

    fuzz, buzz, nuzzled, puzzled

    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_0_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
    ла
    2.27
    ות
    1.93
     on
    1.89
    스
    1.73
    то
    1.66
    ᱘
    1.63
    т
    1.59
    एस
    1.51
    ת
    1.47
    ८
    1.47
    POSITIVE LOGITS
    1.93
    h
    1.80
    <0x80>
    1.55
    在
    1.46
    f
    1.34
    بر
    1.30
    است
    1.25
    ని
    1.12
    اش
    1.10
    ج
    1.09
    Activations Density 0.000%

    No Known Activations