© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203751
    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
    endroit
    0.38
    texts
    0.37
    ᱮ
    0.36
     impr
    0.36
    ốt
    0.35
     cementing
    0.35
    監
    0.35
     empe
    0.34
     क्रमा
    0.34
    ម្បី
    0.33
    POSITIVE LOGITS
     '">'
    0.37
     sapon
    0.35
     ತೆಗೆದುಕೊಳ್ಳ
    0.35
     humiliation
    0.34
     uw
    0.34
     hydrolysis
    0.34
    鋈
    0.34
    荨
    0.34
     Filler
    0.34
     tin
    0.33
    Activations Density 0.000%

    No Known Activations