© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 4-GEMMASCOPE-TRANSCODER-16K
    7. 776
    Prev
    Next
    INDEX
    Explanations

    code and mathematical expressions, specifically those with inequalities, unicode symbols, and iOS code snippets

    oai_token-act-pair · gemini-2.0-flash

    le, <, !=

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    تقاوى
    -0.62
    MemoryWarning
    -0.58
    (!__
    -0.58
    <bos>
    -0.52
    contentLoaded
    -0.52
     Савезне
    -0.52
    AddTagHelper
    -0.50
    IntoConstraints
    -0.48
     contra
    -0.47
    DropColumn
    -0.47
    POSITIVE LOGITS
    DoubleQuotes
    0.61
     =",
    0.58
     Dili
    0.57
    InfoWindow
    0.54
     Continu
    0.54
    LabelTagHelper
    0.54
    }){
    0.53
    MENAFN
    0.53
    argp
    0.53
    曖昧さ回避
    0.52
    Activations Density 4.379%

    No Known Activations