© 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
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12014
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be finding elements of code and formal writing, as well as opinion on political figures.

    oai_token-act-pair · gemini-2.0-flash

    words related to primary or main concepts

    np_token-act-pair-logits · gpt-4o-mini

    main

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    
    -0.58
     ostavi
    -0.52
     BrowserModule
    -0.51
    RepeatedField
    -0.51
    avits
    -0.49
    QMetaType
    -0.48
    dataType
    -0.47
    \{\\
    -0.47
     flames
    -0.47
    rrggbb
    -0.47
    POSITIVE LOGITS
     main
    0.91
    main
    0.77
     Main
    0.72
     MAIN
    0.70
    Main
    0.68
     final
    0.68
     hoved
    0.68
     primary
    0.66
     hlavní
    0.65
    メイン
    0.65
    Activations Density 3.588%

    No Known Activations