© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 8500
    Prev
    Next
    INDEX
    Explanations

    code-related tokens for importing libraries and creating activities

    oai_token-act-pair · gemini-2.0-flash

    app

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     compliqué
    -0.59
     ApJ
    -0.50
    CommandText
    -0.49
    ApJ
    -0.48
    ActiveRecord
    -0.48
     answer
    -0.47
     teis
    -0.47
    gameserver
    -0.47
    openzeppelin
    -0.46
    ampe
    -0.46
    POSITIVE LOGITS
     دیکھیے
    1.06
     '\\;'
    0.86
     désolés
    0.77
    openConnection
    0.73
     himo
    0.72
     kasarigan
    0.71
     CreateTagHelper
    0.71
    twimg
    0.71
    XmlAccessorType
    0.69
    DoubleQuotes
    0.69
    Activations Density 0.065%

    No Known Activations