© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 207266
    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_10_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
    Rena
    0.57
    Release
    0.53
    Classic
    0.52
    Description
    0.51
    Explicit
    0.51
    ש
    0.51
    Selected
    0.50
    Clark
    0.49
    Michael
    0.49
    Publication
    0.49
    POSITIVE LOGITS
    '
    0.64
     ingredient
    0.58
     nitrification
    0.57
     papillary
    0.54
     mitochondria
    0.52
     intakes
    0.52
     auditing
    0.51
     attrezz
    0.51
    :
    0.51
     mediators
    0.49
    Activations Density 0.000%

    No Known Activations