© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 221091
    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
    radi
    0.38
    éfonos
    0.38
     জলাবদ্ধ
    0.38
    Beat
    0.38
    जेस्टिव
    0.37
    iterrows
    0.37
     軽量
    0.37
    
    0.37
    ̛
    0.37
    atu
    0.36
    POSITIVE LOGITS
     اظهار
    0.38
    িল্লা
    0.37
    景色
    0.35
     enormously
    0.34
    টন
    0.34
    。)
    0.34
     చ
    0.33
    ന്ധ
    0.33
     fuss
    0.32
     daftar
    0.32
    Activations Density 0.000%

    No Known Activations