© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19724
    Prev
    Next
    INDEX
    Explanations

    ranked and detailed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_15_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     excelentes
    0.59
    ("//
    0.58
     puertos
    0.54
     immunological
    0.54
    
    0.54
     alcoved
    0.53
    ChooseServer
    0.52
    ../../../
    0.52
    alignParentRight
    0.52
    🛣
    0.50
    POSITIVE LOGITS
        
    0.57
    ly
    0.54
    ال
    0.54
    来源
    0.54
            
    0.51
     not
    0.51
     mis
    0.51
    价格
    0.51
     …
    0.50
    می
    0.50
    Activations Density 0.004%

    No Known Activations