© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 12335
    Prev
    Next
    INDEX
    Explanations

    code-related terms, potentially including variable names, functions, or code structures, often also highlighting the term "leak".

    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_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    kranz
    -0.47
    $_['
    -0.46
    Traducción
    -0.46
     passing
    -0.45
    GUN
    -0.45
    SWEET
    -0.45
    #
    -0.45
     passed
    -0.45
     FetchType
    -0.44
     Luft
    -0.44
    POSITIVE LOGITS
     EnglishChoose
    0.69
     محفوظة
    0.67
    ArgsConstructor
    0.62
     Cæsar
    0.59
    IBar
    0.58
    titleMargin
    0.57
    WebVitals
    0.57
     initComponents
    0.56
     Inhabitants
    0.55
     Beide
    0.55
    Activations Density 1.610%

    No Known Activations