© 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. 91887
    Prev
    Next
    INDEX
    Explanations

    vehicle segment, plant, server, creator

    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
    но
    0.63
     lanz
    0.63
     investigación
    0.61
    нку
    0.58
    <0x0D>
    0.57
     disfruta
    0.54
     reducir
    0.54
     in
    0.53
     Forschungs
    0.53
    ين
    0.52
    POSITIVE LOGITS
    一度
    0.56
    se
    0.54
    차
    0.53
    一百
    0.52
    че
    0.52
    Чер
    0.52
    aging
    0.51
    ാൽ
    0.50
    ሽ
    0.50
    一遍
    0.49
    Activations Density 0.016%

    No Known Activations