© 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. 15958
    Prev
    Next
    INDEX
    Explanations

    words and symbols related to scientific and mathematical publications, especially figures, tables, and formulas

    oai_token-act-pair · gemini-2.0-flash

    scientific/mathematical snippets

    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
     \$
    -0.51
     $
    -0.51
     anledning
    -0.49
    "]="
    -0.48
     թվական
    -0.48
     Critic
    -0.47
     ₹
    -0.46
     дорогие
    -0.46
    ="/
    -0.46
     '@/
    -0.46
    POSITIVE LOGITS
    protoimpl
    0.75
     $(
    0.73
    $(
    0.70
    UserScript
    0.66
    PYX
    0.66
    Spoljašnje
    0.66
    ($(
    0.61
    sizeCache
    0.61
    afficheront
    0.60
     stanovnika
    0.59
    Activations Density 7.706%

    No Known Activations