© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14989
    Prev
    Next
    INDEX
    Explanations

    primarily, mainly, principally

    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_13_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
    '
    0.47
     Desde
    0.45
    ת
    0.45
     previos
    0.44
     años
    0.41
    ան
    0.41
     tahun
    0.39
    Figs
    0.39
     ingles
    0.39
     Dif
    0.39
    POSITIVE LOGITS
     mainly
    0.47
     വേണ്ട
    0.40
     spent
    0.39
    ong
    0.39
    濛
    0.38
    mainly
    0.37
     principalement
    0.37
    үнд
    0.36
    komm
    0.35
    ką
    0.35
    Activations Density 0.048%

    No Known Activations