© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 1858
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas, especially those using symbols like omega, delta, sigma, and exponents.

    oai_token-act-pair · gemini-2.0-flash

    math and physics formulas

    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
     programme
    -0.83
    program
    -0.82
     program
    -0.80
    programma
    -0.80
     programu
    -0.79
     programmet
    -0.77
    Program
    -0.76
     programa
    -0.75
     programma
    -0.74
    programme
    -0.74
    POSITIVE LOGITS
    ibatis
    0.57
    #+#
    0.53
    mybatisplus
    0.50
     distribution
    0.49
    π
    0.48
    orianCalendar
    0.47
    glLoadIdentity
    0.47
    ImageField
    0.46
     상세
    0.46
    GEBURTSDATUM
    0.45
    Activations Density 1.579%

    No Known Activations