© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15829
    Prev
    Next
    INDEX
    Explanations

    mathematical calculations, especially those involving square roots, exponents, and numerical constants

    oai_token-act-pair · gemini-2.0-flash

    Math symbols

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     kasarigan
    -0.88
     ujednoznacz
    -0.82
     nakalista
    -0.77
    EndGlobalSection
    -0.73
    protoimpl
    -0.72
    :✨
    -0.65
    تقاوى
    -0.65
    EndProject
    -0.65
     necesariamente
    -0.65
     <<<<<<<<<<<<<<
    -0.64
    POSITIVE LOGITS
     number
    0.50
     (
    0.46
     Number
    0.46
     IERC
    0.40
     mu
    0.40
    TestingModule
    0.40
     dh
    0.39
     Abp
    0.38
     NUMBER
    0.37
     math
    0.36
    Activations Density 21.291%

    No Known Activations