© 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. 4-GEMMASCOPE-2-TRANSCODER-262K
    7. 193380
    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_4_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
    ও
    0.91
    在
    0.85
    ;
    0.75
    ন
    0.70
    ↵
    0.66
    йки
    0.64
    ल
    0.63
    I
    0.62
    า
    0.61
    이었다
    0.60
    POSITIVE LOGITS
     It
    0.68
    ies
    0.67
    in
    0.65
    TS
    0.65
    RIE
    0.64
    ert
    0.63
    or
    0.63
     or
    0.63
    &\
    0.63
    DA
    0.62
    Activations Density 0.000%

    No Known Activations