© 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-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2799
    Prev
    Next
    INDEX
    Explanations

    legal, medical, and political terminology

    oai_token-act-pair · gemini-2.0-flash

    during

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    
    -0.86
    saraba
    -0.74
    URLException
    -0.64
    uxxxx
    -0.63
     StatefulWidget
    -0.62
    міністра
    -0.61
    +#+#
    -0.60
     cdti
    -0.59
    Rhestr
    -0.59
    djangoproject
    -0.58
    POSITIVE LOGITS
     during
    2.11
     During
    1.84
    during
    1.83
    During
    1.74
     DURING
    1.68
     durante
    1.52
     tijdens
    1.34
    durante
    1.29
    Durante
    1.28
     durant
    1.25
    Activations Density 3.025%

    No Known Activations