© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 192225
    Prev
    Next
    INDEX
    Explanations

    purulent, puro, or rington

    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_4_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     I
    1.20
    ने
    1.10
    ل
    1.05
    r
    0.98
    ag
    0.95
    are
    0.94
    াতাড়ি
    0.91
    ת
    0.91
    AK
    0.90
    ling
    0.89
    POSITIVE LOGITS
    ا
    1.27
    (
    1.15
    ную
    1.02
    р
    0.90
     tại
    0.86
    اة
    0.84
     {
    0.82
    اهرة
    0.80
    的時間
    0.78
     waar
    0.77
    Activations Density 0.000%

    No Known Activations