© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221423
    Prev
    Next
    INDEX
    Explanations

    where explanations come in

    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_31_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
    崽
    0.38
    journ
    0.34
     precisa
    0.33
     Majority
    0.33
     engulf
    0.33
     linh
    0.33
     lector
    0.33
    缃
    0.33
     youll
    0.32
     deva
    0.32
    POSITIVE LOGITS
     बुरी
    0.47
    თ
    0.37
     kötü
    0.36
    琟
    0.35
     приорите
    0.35
    фе
    0.34
     hydrology
    0.34
     normes
    0.33
    Une
    0.33
     miserably
    0.33
    Activations Density 0.006%

    No Known Activations