© 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. 3761
    Prev
    Next
    INDEX
    Explanations

    words related to mathematics

    oai_token-act-pair · gemini-2.0-flash

    data analysis, machine learning

    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
     الحره
    -0.73
    RegistryLite
    -0.69
     CreateTagHelper
    -0.69
    المناصب
    -0.68
    NewRow
    -0.66
    tagHelperRunner
    -0.64
    awtextra
    -0.63
    __':
    -0.62
    DotNetBar
    -0.62
    patine
    -0.60
    POSITIVE LOGITS
     signal
    0.70
    signal
    0.61
    Signal
    0.60
     image
    0.59
     Signal
    0.57
     machine
    0.55
     statistics
    0.53
     fluid
    0.50
    image
    0.50
     linear
    0.50
    Activations Density 8.056%

    No Known Activations