© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40040
    Prev
    Next
    INDEX
    Explanations

    column name

    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_3_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
     complementar
    0.75
    ra
    0.70
    ра
    0.69
    ول
    0.69
    י
    0.68
    ك
    0.66
    all
    0.64
     ကျွန်
    0.63
    J
    0.63
    ঁজ
    0.63
    POSITIVE LOGITS
    í
    0.77
    á
    0.71
    مون
    0.61
    å
    0.61
    sin
    0.59
    rik
    0.57
    sha
    0.56
    ik
    0.55
    uvat
    0.55
    se
    0.54
    Activations Density 0.002%

    No Known Activations