© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 166075
    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
     Fri
    0.36
    给自己
    0.36
    lined
    0.34
    (_,
    0.34
     bas
    0.34
    Fri
    0.34
     undertaken
    0.33
    感知
    0.33
     commissioned
    0.33
     Multivariate
    0.33
    POSITIVE LOGITS
     glPopMatrix
    0.40
    Ϫ
    0.38
    
    0.38
     হজ
    0.38
    jfif
    0.38
    يزة
    0.38
    梖
    0.37
    のエ
    0.37
     integrante
    0.36
    喺
    0.36
    Activations Density 0.000%

    No Known Activations