© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 205902
    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
    itchie
    0.42
    scr
    0.42
    ಾರದ
    0.39
     प्रतियोग
    0.38
     寸
    0.38
    ຈາກ
    0.38
    າວ
    0.38
     комплекса
    0.37
    🇨
    0.37
    até
    0.37
    POSITIVE LOGITS
    Musik
    0.38
    צא
    0.38
     উত্তম
    0.37
     regol
    0.36
     Akufo
    0.36
     вкус
    0.35
     preschool
    0.35
     Fußball
    0.35
     polvo
    0.34
     stycz
    0.34
    Activations Density 0.000%

    No Known Activations