© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 253525
    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_56_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
     הי
    0.38
    ";
    0.38
    executive
    0.37
    ein
    0.36
    orElse
    0.36
    fum
    0.36
    uç
    0.36
    깨
    0.36
    յան
    0.36
     Eins
    0.35
    POSITIVE LOGITS
     parece
    0.77
     enjoys
    0.67
     webpages
    0.63
     cuatro
    0.62
     voglio
    0.60
     elizabeth
    0.60
     rencontres
    0.59
     Parece
    0.58
     Meters
    0.56
     Г
    0.55
    Activations Density 0.000%

    No Known Activations