© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 125410
    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_37_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
    汙
    0.38
     Gebä
    0.38
     saepe
    0.37
     kick
    0.37
     Gettys
    0.35
    每
    0.35
     intersected
    0.35
     nyingi
    0.35
    每一
    0.35
     பண்டைய
    0.35
    POSITIVE LOGITS
    Met
    0.40
    憫
    0.37
     Met
    0.34
    BBB
    0.34
     alak
    0.34
     Boutique
    0.34
     الوزراء
    0.34
    ::::::::
    0.34
     ممالک
    0.34
     থাকেন
    0.33
    Activations Density 0.000%

    No Known Activations