© 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. 8639
    Prev
    Next
    INDEX
    Explanations

    connecting tasks and data flows

    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
    Negative Logits
     ప్రపంచ
    0.54
     вважа
    0.51
     സ്
    0.50
     Aks
    0.50
     Among
    0.50
     naal
    0.48
     Yoo
    0.48
    inę
    0.48
    o
    0.48
     ŝ
    0.47
    POSITIVE LOGITS
    cron
    0.55
     appareils
    0.52
    alogical
    0.50
     médicament
    0.50
     appareil
    0.49
     estrel
    0.48
     exécut
    0.47
    denes
    0.47
     kesalahan
    0.47
    bien
    0.46
    Activations Density 0.044%

    No Known Activations