© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19731
    Prev
    Next
    INDEX
    Explanations

    Wilson Score Interval

    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_15_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
    MAN
    0.59
    s
    0.54
    ंद
    0.52
    ção
    0.51
    另一
    0.51
    meth
    0.50
    ness
    0.48
    icamente
    0.48
    d
    0.47
    Д
    0.47
    POSITIVE LOGITS
    CSharp
    0.62
     สนาม
    0.55
     הת
    0.54
     반지
    0.54
     pardon
    0.53
     Tattha
    0.52
     внутрен
    0.52
    annten
    0.52
     живот
    0.52
     विभक्ति
    0.51
    Activations Density 0.000%

    No Known Activations