© 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. 78321
    Prev
    Next
    INDEX
    Explanations

    job postings and lists

    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
    Negative Logits
    jší
    1.48
    ৫
    1.48
     can
    1.22
    ול
    1.20
    ول
    1.19
     wenige
    1.19
     malice
    1.16
    '
    1.16
     ৩০
    1.16
     这里
    1.16
    POSITIVE LOGITS
    s
    1.95
    و
    1.94
    ς
    1.87
    ی
    1.70
    ्स
    1.52
    س
    1.51
    سازی
    1.48
    the
    1.43
    وپ
    1.41
    سون
    1.41
    Activations Density 0.000%

    No Known Activations