© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 9473
    Prev
    Next
    INDEX
    Explanations

    the term "NGX" in computer code, in association with other capitalized terms

    oai_token-act-pair · gemini-2.0-flash

    NG

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     MainAxisSize
    -0.56
    RectangleBorder
    -0.56
    ArgumentParser
    -0.51
     cherchés
    -0.50
     насеље
    -0.47
    WebpackPlugin
    -0.45
    hér
    -0.45
     cherchez
    -0.44
     scolaires
    -0.44
     menger
    -0.44
    POSITIVE LOGITS
    LEncoder
    0.67
    thâu
    0.65
     reaſon
    0.62
    Grazie
    0.60
    évaluateur
    0.58
     Constitucional
    0.57
     betweenstory
    0.57
     Shakspeare
    0.57
     mastered
    0.57
     fathoms
    0.55
    Activations Density 4.500%

    No Known Activations