© 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. 40719
    Prev
    Next
    INDEX
    Explanations

    navigation plan controller delegate

    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
     Celle
    0.62
     Bloch
    0.57
     Chau
    0.56
     Veloc
    0.55
     Blob
    0.53
     Ruh
    0.53
    顐
    0.53
     Novi
    0.52
     alimentare
    0.52
     Riet
    0.52
    POSITIVE LOGITS
    r
    0.77
    i
    0.75
    い
    0.70
    ו
    0.70
    ي
    0.68
    $
    0.66
    면
    0.62
    म
    0.62
    ف
    0.61
    માં
    0.59
    Activations Density 0.001%

    No Known Activations