© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 12396
    Prev
    Next
    INDEX
    Explanations

    sequences of exponents within LaTeX math mode

    oai_token-act-pair · gemini-2.0-flash

    Parenthesis and brackets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    ^{
    -2.25
    )^{
    -1.70
     ^{
    -1.59
    }^{
    -1.38
    ]^{
    -1.37
    $^{
    -1.27
    ^(
    -1.21
    })^{
    -1.21
    ^{\
    -1.14
    <sup>
    -1.10
    POSITIVE LOGITS
    WaitGroup
    0.65
    rshire
    0.56
    XmlAccessType
    0.56
    DoubleQuotes
    0.54
    
    0.54
     Patches
    0.53
    wachs
    0.52
    CURLOPT
    0.49
     restTemplate
    0.48
    TORE
    0.48
    Activations Density 1.373%

    No Known Activations