© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 13004
    Prev
    Next
    INDEX
    Explanations

    the prefix "Py" or "py", likely related to Python or chemical prefixes

    oai_token-act-pair · gemini-2.0-flash

    programming or coding syntax

    np_token-act-pair-logits · gpt-4o-mini

    py or pi

    np_max-act-logits · gemini-2.0-flash
    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
     l
    -0.54
     up
    -0.44
    wad
    -0.43
     lau
    -0.43
    te
    -0.42
     b
    -0.41
    liver
    -0.41
    tet
    -0.40
     small
    -0.40
    w
    -0.40
    POSITIVE LOGITS
    RenderAtEndOf
    0.90
     للمعارف
    0.85
     kasarigan
    0.85
    endphp
    0.85
     ComVisible
    0.82
     AssemblyProduct
    0.81
     يتيمه
    0.81
    setVerticalGroup
    0.80
     AssemblyTitle
    0.80
    ########.
    0.79
    Activations Density 0.379%

    No Known Activations