© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 5430
    Prev
    Next
    INDEX
    Explanations

    code documentation and exceptions in Java code

    oai_token-act-pair · gemini-2.0-flash

    "///</"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    LookAnd
    -3.63
    oredCriteria
    -3.52
     Италијани
    -3.38
     Roskov
    -3.38
    webElementXpaths
    -3.34
    ьаж
    -3.30
     ویکی‌پدی
    -3.20
    RegressionTest
    -3.19
    parsedMessage
    -3.17
    Personensuche
    -3.11
    POSITIVE LOGITS
    LLI
    0.60
    ‍
    0.58
     
    0.57
    DefaultValue
    0.55
    <table>
    0.54
    Polen
    0.54
    <tbody>
    0.53
    Galeria
    0.53
     eslint
    0.52
    fim
    0.52
    Activations Density 7.636%

    No Known Activations