© 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. 29-GEMMASCOPE-2-TRANSCODER-262K
    7. 77474
    Prev
    Next
    INDEX
    Explanations

    15th, 100th, 10th

    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_29_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
     Roche
    0.47
    תיים
    0.42
    Roche
    0.42
     René
    0.42
    Antae
    0.41
     idé
    0.40
    ydı
    0.40
     উপসং
    0.40
    捭
    0.39
     విశ్వ
    0.39
    POSITIVE LOGITS
     concerned
    0.36
     manor
    0.34
    飾
    0.34
     curation
    0.33
     estate
    0.33
     compile
    0.33
     preserving
    0.33
    (_)
    0.33
     conserving
    0.33
     play
    0.32
    Activations Density 0.004%

    No Known Activations