© 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. 197475
    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
    ு
    0.63
    at
    0.63
    د
    0.62
    끈
    0.54
    ्रिया
    0.53
    o
    0.52
    ів
    0.52
    This
    0.52
    ع
    0.52
    is
    0.50
    POSITIVE LOGITS
     kişinin
    0.57
    𝓗
    0.55
    ATION
    0.55
    キロ
    0.55
     በር
    0.55
     Վ
    0.54
    方が
    0.54
     खरीद
    0.53
     ห
    0.53
     waż
    0.53
    Activations Density 0.000%

    No Known Activations