© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 57173
    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_11_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
    eling
    0.54
     со
    0.54
    /
    0.53
     +
    0.53
     chur
    0.53
     soot
    0.53
     irreg
    0.52
     )
    0.51
    </blockquote>
    0.49
     et
    0.49
    POSITIVE LOGITS
    神经
    0.57
    簫
    0.55
    我们
    0.53
    你想
    0.53
    類型
    0.53
    മല്ല
    0.52
    語言
    0.52
    テスト
    0.52
    我們
    0.52
    亚马逊
    0.50
    Activations Density 0.000%

    No Known Activations