© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9799
    Prev
    Next
    INDEX
    Explanations

    LaTeX math environments and expressions, especially those involving fractions and subscripts with the labels "ex", "in", "esc" and "aligned"

    oai_token-act-pair · gemini-2.0-flash

    {

    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
    Negative Logits
    {
    -1.44
    {
    -1.10
    {$
    -0.90
    {\
    -0.81
    {{
    -0.75
    {!
    -0.73
    {}'.
    -0.73
    {(
    -0.71
    \{
    -0.71
    ${
    -0.70
    POSITIVE LOGITS
    IonicModule
    0.72
     OFDb
    0.71
    rawDesc
    0.68
    ArrowToggle
    0.68
    UnknownFields
    0.67
    StructEnd
    0.66
    +#+
    0.63
    :✨
    0.61
    GEBURTSDATUM
    0.60
    ;->
    0.58
    Activations Density 1.128%

    No Known Activations