© 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. 13999
    Prev
    Next
    INDEX
    Explanations

    LaTeX mathematical environments and equations

    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
     disambiguazione
    -0.85
    MessageTagHelper
    -0.78
    :✨
    -0.77
    Üdv
    -0.76
     سكانية
    -0.75
     JpaRepository
    -0.75
     الحره
    -0.75
    بوابة
    -0.75
    참고
    -0.75
     مشين
    -0.74
    POSITIVE LOGITS
    <bos>
    0.46
    r
    0.46
    мка
    0.45
    //
    0.45
    ${
    0.45
    i
    0.42
    y
    0.41
    $
    0.40
    '
    0.40
     laure
    0.38
    Activations Density 3.832%

    No Known Activations