© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 5278
    Prev
    Next
    INDEX
    Explanations

    mentions of computer code and programming

    oai_token-act-pair · gemini-2.0-flash

    keywords related to code and programming

    np_token-act-pair-logits · gpt-4o-mini

    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_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ModelSerializer
    -0.70
     MainAxisSize
    -0.66
    DoubleQuotes
    -0.65
    tvguidetime
    -0.63
    KommentareTeilen
    -0.60
     ArrayAdapter
    -0.58
     initComponents
    -0.58
    kuuta
    -0.57
    tamento
    -0.54
    تقاوى
    -0.53
    POSITIVE LOGITS
    Inflater
    0.54
    FormTagHelper
    0.49
     segnale
    0.47
    toms
    0.47
    ">'+
    0.46
    encodeWith
    0.46
    JspWriter
    0.46
    Bioaccumulative
    0.46
     للمعارف
    0.45
    INCREF
    0.45
    Activations Density 3.747%

    No Known Activations