© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173384
    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
    destination
    0.38
     marketplaces
    0.33
     destination
    0.32
    ೖ
    0.32
    لمان
    0.32
     disposition
    0.31
    cidas
    0.31
    ет
    0.31
    direction
    0.31
     notation
    0.31
    POSITIVE LOGITS
     जुनून
    0.38
    जिए
    0.32
    
    0.31
     fué
    0.31
     became
    0.31
     им
    0.30
     evolucion
    0.30
     செ
    0.30
     snag
    0.30
     শোক
    0.30
    Activations Density 0.000%

    No Known Activations