© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 133696
    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_50_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
    DIS
    0.44
    DOUT
    0.42
    瓣
    0.40
     تباہ
    0.39
    ítě
    0.38
     تبدی
    0.37
    裆
    0.37
    बलेट
    0.37
    ৈর
    0.36
    溯
    0.36
    POSITIVE LOGITS
     kun
    1.63
     Kun
    1.48
    Kun
    1.45
    kun
    1.42
     Cun
    1.09
    昆
    1.05
    kund
    1.04
    cun
    0.95
     cun
    0.93
     Kün
    0.91
    Activations Density 0.000%

    No Known Activations