© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 7346
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting for mathematical equations

    oai_token-act-pair · gemini-2.0-flash

    operations or functions in programming contexts

    np_token-act-pair-logits · gpt-4o-mini
    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
     }}{
    -0.50
     »)
    -0.49
     ){
    -0.49
     }}$}
    -0.48
    InitVars
    -0.48
     ){
    -0.48
    \
    -0.48
    ("")){
    -0.47
    rama
    -0.46
     ))
    -0.45
    POSITIVE LOGITS
    CloseOperation
    0.69
     oprot
    0.68
     convertView
    0.60
     AssemblyProduct
    0.60
    InstanceState
    0.60
    Билгалдахарш
    0.59
    Xaml
    0.59
    ніципалі
    0.59
     وتسجيلات
    0.56
    extAlignment
    0.56
    Activations Density 2.523%

    No Known Activations