© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 50231
    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_10_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
    ي
    0.57
     visceral
    0.45
    帖
    0.44
    නු
    0.44
    尊
    0.44
     lucru
    0.43
     lir
    0.43
    蒙
    0.43
    ↔
    0.43
     marchand
    0.43
    POSITIVE LOGITS
     同じ
    0.58
     问题
    0.55
     Grammar
    0.51
     همین
    0.51
     Religion
    0.51
     問題
    0.51
     Criminal
    0.50
     言っ
    0.47
     名前
    0.47
     หมด
    0.46
    Activations Density 0.000%

    No Known Activations