© 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. 78419
    Prev
    Next
    INDEX
    Explanations

    cardi words

    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
    。
    1.87
    $.
    1.73
     to
    1.70
    م
    1.69
     l
    1.68
    In
    1.57
     s
    1.52
     e
    1.52
    。\
    1.50
     In
    1.49
    POSITIVE LOGITS
    n
    1.86
    ри
    1.84
    ută
    1.55
    nél
    1.49
    يه
    1.37
    ರ
    1.37
    nX
    1.35
    nál
    1.34
    ת
    1.34
    ra
    1.32
    Activations Density 0.000%

    No Known Activations