© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 35079
    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_50_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
     Frequency
    0.48
    抨
    0.44
     globales
    0.44
     Dismiss
    0.43
     अतिक्रमण
    0.42
    Frequency
    0.42
     Scoring
    0.41
    鴎
    0.41
     Filing
    0.41
     फाइल
    0.41
    POSITIVE LOGITS
     pretty
    0.57
    pretty
    0.54
    Pretty
    0.40
    cas
    0.39
    apon
    0.38
     tumbling
    0.38
    arge
    0.36
    ca
    0.35
     caps
    0.35
     Stokes
    0.35
    Activations Density 0.000%

    No Known Activations