© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 127525
    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_3_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
     protect
    0.81
    تی
    0.80
    سی
    0.80
    त
    0.78
     dosy
    0.75
     ganado
    0.73
     BREAK
    0.72
     simulate
    0.71
     destroy
    0.70
     contatt
    0.70
    POSITIVE LOGITS
    ä
    0.81
    é
    0.69
    ج
    0.64
    ClO
    0.62
    hav
    0.61
    hydrox
    0.57
    README
    0.56
    hind
    0.54
    ü
    0.53
    Disc
    0.52
    Activations Density 0.000%

    No Known Activations