© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 7627
    Prev
    Next
    INDEX
    Explanations

    references to labeled sections or subsections within a paper

    oai_token-act-pair · gemini-2.0-flash

    say "section"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     gainera
    -0.59
     <=",
    -0.54
    Espèce
    -0.51
    __':
    -0.51
    IUrlHelper
    -0.50
     defaultstate
    -0.49
     ModelExpression
    -0.48
    NOPQRST
    -0.48
    parsedMessage
    -0.48
    ArrowToggle
    -0.48
    POSITIVE LOGITS
     section
    2.41
     sections
    1.94
    section
    1.82
     Section
    1.79
    Section
    1.66
     SECTION
    1.64
     subsection
    1.55
    sections
    1.52
     sección
    1.48
     sezione
    1.46
    Activations Density 2.881%

    No Known Activations