© 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
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-262K
    4. 5242
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_262k_l0_medium
    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
     préciser
    0.94
     Sprache
    0.92
     aussi
    0.91
     réfléch
    0.91
     Président
    0.91
     correspondant
    0.90
     réflexion
    0.90
    佣
    0.90
     édition
    0.87
     étaient
    0.87
    POSITIVE LOGITS
    *
    0.85
            
    0.75
    .
    0.74
    ga
    0.73
    en
    0.73
    <
    0.72
    tet
    0.72
    o
    0.71
      
    0.67
    det
    0.66
    Activations Density 0.000%

    No Known Activations