© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 2858
    Prev
    Next
    INDEX
    Explanations

    TeX mathematical notation within scientific papers

    oai_token-act-pair · gemini-2.0-flash

    programming-related terms or snippets

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

    Math equations

    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
    ритори
    -0.54
     sentinel
    -0.51
     Voiture
    -0.48
     cradle
    -0.46
    ganu
    -0.45
     spotting
    -0.45
     Cervantes
    -0.44
     Challenger
    -0.43
     Lanz
    -0.43
     ATLAS
    -0.43
    POSITIVE LOGITS
    LookAnd
    0.76
     OFDb
    0.75
    UnitTesting
    0.65
    setViewName
    0.64
     jScrollPane
    0.61
    UnusedPrivate
    0.60
    jsxFileName
    0.59
    Carriera
    0.59
     المعيارى
    0.59
    endphp
    0.57
    Activations Density 6.066%

    No Known Activations