© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 37759
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_11_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    to
    0.70
    в
    0.64
    io
    0.64
     are
    0.59
    Lung
    0.55
    روی
    0.54
    Link
    0.54
    trn
    0.54
    ira
    0.51
     Пор
    0.51
    POSITIVE LOGITS
     conteú
    0.58
     maî
    0.56
    éph
    0.54
    ！）
    0.54
     laisser
    0.54
    ↵
    0.53
    ابقة
    0.52
     maîtrise
    0.52
     précédente
    0.51
     согласо
    0.51
    Activations Density 0.000%

    No Known Activations