© 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. 1510
    Prev
    Next
    INDEX
    Explanations

    java import statements

    oai_token-act-pair · gemini-2.0-flash

    Java Swing 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_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
    ...');
    -0.59
    !")
    -0.56
    ."));
    -0.55
    avoir
    -0.53
    felves
    -0.52
     :)</
    -0.52
    ,»
    -0.51
    .」
    -0.51
    ...")
    -0.50
    ſelves
    -0.50
    POSITIVE LOGITS
    RegressionTest
    0.68
    JMenuBar
    0.67
    HtmlAttribute
    0.66
    الدراسه
    0.64
    kloped
    0.64
     تضيفلها
    0.64
    JMenu
    0.63
    makeConstraints
    0.63
    +#+
    0.63
    BASELINE
    0.62
    Activations Density 3.102%

    No Known Activations