© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53265
    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_31_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
     https
    0.71
     http
    0.55
    https
    0.54
    }~\
    0.39
    льский
    0.39
    следования
    0.38
     www
    0.37
     bede
    0.37
    Ꮁ
    0.36
     Фонбет
    0.36
    POSITIVE LOGITS
     නමුත්
    0.39
     Tonic
    0.38
     সাক্ষাৎ
    0.37
     പക്ഷേ
    0.37
     nødv
    0.35
     Clint
    0.35
     Fit
    0.34
    insky
    0.34
    絊
    0.34
     ancak
    0.33
    Activations Density 0.000%

    No Known Activations