© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 220166
    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_31_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
    ($
    0.37
    ライズ
    0.37
     pipes
    0.37
    ֤
    0.36
     mug
    0.36
     FFA
    0.36
    Biological
    0.35
    ayant
    0.35
     बेस्ट
    0.34
    épid
    0.34
    POSITIVE LOGITS
    ustrated
    0.39
     Ото
    0.36
    𒉺
    0.36
     количеством
    0.35
    潛
    0.35
    潜
    0.34
     кана
    0.34
    okon
    0.34
     ছাড়াও
    0.34
    ებისა
    0.34
    Activations Density 0.000%

    No Known Activations