© 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. 193615
    Prev
    Next
    INDEX
    Explanations

    langchain chains

    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
    i
    0.63
     n
    0.56
    e
    0.53
    ी
    0.52
     i
    0.52
    º
    0.50
    ي
    0.50
    who
    0.50
     than
    0.49
     H
    0.49
    POSITIVE LOGITS
    бліоте
    0.59
     sparsim
    0.52
     compléter
    0.51
    InEx
    0.51
     fournis
    0.50
     organismes
    0.50
     εργ
    0.49
    ⚐
    0.49
    ಬ್ಬಿಣ
    0.49
    ੳ
    0.49
    Activations Density 0.000%

    No Known Activations