© 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. 29290
    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
    л
    0.78
    is
    0.74
    l
    0.73
    ι
    0.68
    oches
    0.67
    ilte
    0.66
    il
    0.66
    ال
    0.65
    க்கிறது
    0.65
    olines
    0.65
    POSITIVE LOGITS
     jury
    0.77
     automate
    0.73
     juror
    0.71
     fudge
    0.70
     frame
    0.68
     FRAME
    0.67
    ส
    0.67
     pilot
    0.66
     mediator
    0.66
     goalie
    0.66
    Activations Density 0.000%

    No Known Activations