© 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. 166574
    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
     independência
    0.37
    SIMPLEX
    0.36
     crustaceans
    0.36
     coolers
    0.36
    Cells
    0.35
     생각
    0.35
     номина
    0.34
    戏
    0.34
     crabs
    0.34
     hücre
    0.34
    POSITIVE LOGITS
     カジュアル
    0.36
    ীয়
    0.35
    有個
    0.34
    降低
    0.34
     অনুরাগ
    0.33
    क्टूबर
    0.33
    portal
    0.33
    ាត់
    0.33
    клон
    0.33
     असा
    0.33
    Activations Density 0.000%

    No Known Activations