Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14441
    Prev
    Next
    INDEX
    Explanations

    LaTeX or other similar equation syntax and mathematical symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    migrationBuilder
    -0.73
    RectangleBorder
    -0.73
    AndroidJUnit
    -0.72
    SourceChecksum
    -0.72
    GEBURTSDATUM
    -0.70
    offsetof
    -0.68
    DockStyle
    -0.64
    openzeppelin
    -0.64
     cref
    -0.63
     مرئيه
    -0.62
    POSITIVE LOGITS
    }^{-\
    0.45
     [{
    
    0.40
     RSSSF
    0.39
    épend
    0.39
    ...",
    0.39
    ^{-\
    0.39
    檚
    0.37
    )}(\
    0.36
    )--(
    0.36
     وتسجيلات
    0.35
    Activations Density 10.826%

    No Known Activations