© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4956
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and symbols like function names, parameters, and code blocks

    oai_token-act-pair · gemini-2.0-flash

    say "= symbol"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
    [
    -1.03
    ({
    -0.94
    {
    -0.88
    ["
    -0.85
    (
    -0.85
    (-
    -0.83
    [[
    -0.82
    ((
    -0.81
    [{
    -0.81
    (&
    -0.80
    POSITIVE LOGITS
    NewUrlParser
    0.50
     '\\;'
    0.48
    ,$_
    0.48
    şiv
    0.46
     propOrder
    0.44
    WebVitals
    0.43
    ็จ
    0.42
     gages
    0.41
    ={},
    0.41
    =[],
    0.40
    Activations Density 5.816%

    No Known Activations