© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 200809
    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_46_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
    waj
    0.39
     स्कैनर
    0.38
     প্রাণে
    0.37
     unsc
    0.37
     sort
    0.37
    扫描
    0.36
     reimb
    0.35
    印
    0.35
    scanner
    0.35
     trình
    0.34
    POSITIVE LOGITS
     Requirement
    0.45
     русских
    0.43
     प्राथमिकता
    0.39
     prioritise
    0.39
     приорите
    0.39
     Fukuoka
    0.38
    ெடு
    0.38
     তাকে
    0.38
     BadRequest
    0.38
     Perp
    0.38
    Activations Density 0.000%

    No Known Activations