© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10261
    Prev
    Next
    INDEX
    Explanations

    words and symbols within scientific publications on quantum physics, superconductivity, and thermal dynamics

    oai_token-act-pair · gemini-2.0-flash

    physics/lattice sites/charge

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
    GenerationType
    -0.73
     متعلقه
    -0.67
    EnableWeb
    -0.54
    cyd
    -0.52
    代目
    -0.52
    viewType
    -0.51
    RegressionTest
    -0.51
    shadowOpacity
    -0.51
    HtmlAttribute
    -0.50
    ViewImports
    -0.50
    POSITIVE LOGITS
    ClientRect
    0.63
    NavigationView
    0.63
    extField
    0.55
    ichier
    0.55
    mdan
    0.54
    ulpt
    0.54
     مشين
    0.52
    arraycopy
    0.51
    extAlignment
    0.50
    tième
    0.50
    Activations Density 3.402%

    No Known Activations