© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 37381
    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_57_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
    dui
    0.42
    いたら
    0.41
     못
    0.39
     keuntungan
    0.39
     DUI
    0.38
     Inheritance
    0.38
     utu
    0.37
     WHETHER
    0.37
    iosa
    0.36
    пати
    0.36
    POSITIVE LOGITS
    red
    0.44
    RED
    0.43
    yphenyl
    0.43
    ishan
    0.43
    zip
    0.42
     yal
    0.41
    ylis
    0.41
    렙
    0.39
    amless
    0.38
    Oe
    0.38
    Activations Density 0.000%

    No Known Activations