© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 28770
    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_10_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
    ین
    0.54
    ี้
    0.47
     عارفين
    0.45
    ت
    0.45
    IMC
    0.44
     Welding
    0.44
    一口
    0.43
    ات
    0.43
     Бі
    0.43
    。”
    0.42
    POSITIVE LOGITS
     eccentric
    0.54
    '
    0.50
     buena
    0.47
     dick
    0.47
     extermin
    0.46
     inconsider
    0.46
     sortir
    0.46
     jerk
    0.46
     sard
    0.46
     membrane
    0.45
    Activations Density 0.000%

    No Known Activations