© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 171516
    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_20_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
     Similarly
    0.42
    っぽ
    0.40
     ステン
    0.40
     similarly
    0.39
     прият
    0.39
    昷
    0.39
    
    0.38
    confidence
    0.38
     సా
    0.38
    elope
    0.38
    POSITIVE LOGITS
    şık
    0.49
     externes
    0.48
    ूर्ण
    0.46
     comportement
    0.46
     aiguë
    0.46
     arrêt
    0.45
    総
    0.45
     grü
    0.45
     été
    0.44
    ंना
    0.44
    Activations Density 0.000%

    No Known Activations