© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    code snippets that contain generics, iterators, and math equations

    oai_token-act-pair · 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
     OFDb
    -0.76
    DoubleQuotes
    -0.66
     AssemblyCulture
    -0.65
    談社
    -0.60
    NOPQRST
    -0.59
    TestingModule
    -0.57
    CloseOperation
    -0.56
    uede
    -0.56
     Infórmanos
    -0.56
     >=",
    -0.54
    POSITIVE LOGITS
     it
    3.31
    它
    2.08
    It
    2.05
     оно
    2.05
     It
    2.02
    it
    1.80
    มัน
    1.73
     nó
    1.70
     它
    1.69
     its
    1.57
    Activations Density 8.120%

    No Known Activations