© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 222104
    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
     prioritise
    0.53
     fraude
    0.53
    缛
    0.50
     понимать
    0.49
     tragen
    0.49
     sah
    0.48
     fathom
    0.48
     mockery
    0.48
     grudge
    0.48
    hiana
    0.48
    POSITIVE LOGITS
     M
    0.53
     NIH
    0.48
     Invited
    0.46
    विच
    0.46
     Approved
    0.45
     Relax
    0.45
     (?,
    0.44
     Appearance
    0.44
     American
    0.44
    ([
    0.44
    Activations Density 0.000%

    No Known Activations