© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 149737
    Prev
    Next
    INDEX
    Explanations

    se

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     this
    0.61
     in
    0.55
     e
    0.55
     be
    0.51
     do
    0.48
    this
    0.48
     de
    0.47
     for
    0.47
     not
    0.45
     form
    0.45
    POSITIVE LOGITS
     carácter
    0.61
    त
    0.59
     знать
    0.57
     считать
    0.56
     caractér
    0.56
     кажется
    0.55
     характеризу
    0.55
     biết
    0.54
    Know
    0.52
     знает
    0.52
    Activations Density 0.002%

    No Known Activations