© 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. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6680
    Prev
    Next
    INDEX
    Explanations

    code-related keywords like `var`, `function`, and `game`

    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_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    tagHelperRunner
    -0.45
    تقاوى
    -0.44
     InputDecoration
    -0.43
    msgTypes
    -0.43
    はじめに
    -0.42
    setCellStyle
    -0.40
     procu
    -0.39
    BeginInit
    -0.39
    openConnection
    -0.37
    numRows
    -0.36
    POSITIVE LOGITS
    WebMethod
    0.71
    oğlu
    0.68
    EnableWeb
    0.60
    SourceChecksum
    0.60
    vieja
    0.59
     Brewer
    0.59
    aksanaan
    0.57
     navigator
    0.57
    meo
    0.57
     NSCoder
    0.57
    Activations Density 1.469%

    No Known Activations