© 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. 8172
    Prev
    Next
    INDEX
    Explanations

    words that are typically found in discussions about education, schools, or learning in children

    oai_token-act-pair · gemini-2.0-flash

    school academic performance

    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
    aarrggbb
    -0.80
    存于互联网档案馆
    -0.79
     IBOutlet
    -0.77
     '\\;'
    -0.75
    UnusedPrivate
    -0.75
     оригіналу
    -0.75
     AssemblyProduct
    -0.72
    setVerticalGroup
    -0.71
    tagHelperRunner
    -0.70
     MaterialApp
    -0.69
    POSITIVE LOGITS
     članak
    0.45
     ex
    0.42
    ANA
    0.41
     />\
    0.40
     Aprile
    0.40
     prof
    0.39
     Ex
    0.39
     pasang
    0.39
    ❉
    0.38
     leb
    0.37
    Activations Density 2.965%

    No Known Activations