© 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. 30830
    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
    बाट
    0.39
     ute
    0.37
    ಹ
    0.36
     epochs
    0.34
     هار
    0.33
    ブリッド
    0.33
    モニター
    0.33
    CopyTo
    0.33
    шла
    0.32
     hurdles
    0.32
    POSITIVE LOGITS
     člov
    0.37
    感
    0.37
     እየ
    0.36
     (|
    0.36
     풀
    0.36
    ("\\
    0.36
     腰
    0.36
    قامة
    0.36
    🎌
    0.36
    eless
    0.35
    Activations Density 0.000%

    No Known Activations