© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 12542
    Prev
    Next
    INDEX
    Explanations

    LaTeX code related to mathematical equations, especially fractions, limits, trigonometric functions, and polar coordinates.

    oai_token-act-pair · gemini-2.0-flash

    mathematical writing

    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
     nahilalakip
    -0.60
    awaiter
    -0.58
     JpaRepository
    -0.56
    niająca
    -0.55
     cappello
    -0.50
    bben
    -0.49
    lave
    -0.49
    ignez
    -0.49
    rungsseite
    -0.48
     AppColors
    -0.48
    POSITIVE LOGITS
    />";
    0.56
     betweenstory
    0.54
    cipar
    0.52
     (;;
    0.50
    তথ্যসূত্র
    0.49
    estimators
    0.48
    rump
    0.48
    ագրություններ
    0.48
    erdings
    0.48
    Тарихы
    0.48
    Activations Density 1.390%

    No Known Activations