© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10026
    Prev
    Next
    INDEX
    Explanations

    references to Central and South America

    oai_token-act-pair · gemini-2.0-flash

    Central

    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
    Not in Any Lists

    No Comments

    Negative Logits
    cin
    -0.50
    ready
    -0.50
    mixins
    -0.50
    /***/
    -0.49
    以上
    -0.49
     ready
    -0.48
    ￡
    -0.47
    :✨
    -0.47
    ViewImports
    -0.46
    стра
    -0.44
    POSITIVE LOGITS
    setVerticalGroup
    0.78
    thâu
    0.75
    lossians
    0.74
     initComponents
    0.69
     Мексичка
    0.69
    AccessorTable
    0.69
    ագրություններ
    0.68
    Portály
    0.66
    MessageTagHelper
    0.66
    CloseOperation
    0.65
    Activations Density 0.645%

    No Known Activations