© 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
    2. Gemma-2-2B
    3. 23-GEMMASCOPE-TRANSCODER-16K
    4. 10843
    Prev
    Next
    INDEX
    Explanations

    words related to higher-order physics, especially gauge theory, transformations, and ghost fields

    oai_token-act-pair · gemini-2.0-flash

    Physics and gauge theories

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    InSection
    -0.64
    endpush
    -0.51
    XmlRootElement
    -0.48
    AMIENTO
    -0.48
    Newswire
    -0.47
    PRWEB
    -0.46
    apimachinery
    -0.45
     Normdatei
    -0.45
     referrerpolicy
    -0.44
     feather
    -0.44
    POSITIVE LOGITS
    MLLoader
    0.64
    MessageTagHelper
    0.62
     initComponents
    0.61
    AnchorTagHelper
    0.57
    enumii
    0.55
     BoxFit
    0.54
    ://$
    0.54
     gesteld
    0.54
    :✨
    0.53
    ]_{
    0.52
    Activations Density 1.779%

    No Known Activations