© 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. 6639
    Prev
    Next
    INDEX
    Explanations

    C++ code elements, especially related to a game AI.

    oai_token-act-pair · gemini-2.0-flash

    programming-related keywords

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

    ->

    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
     ویکی‌پدیا
    -0.71
    SequentialGroup
    -0.68
     mergeFrom
    -0.59
     typelib
    -0.58
     متعلقه
    -0.56
     ویکی
    -0.54
    ErrUnexpectedEOF
    -0.52
    NameInMap
    -0.51
    NOPQRST
    -0.50
    ValueStyle
    -0.50
    POSITIVE LOGITS
    Datuak
    0.60
    cshtml
    0.57
    ſelf
    0.56
    τία
    0.55
    yana
    0.50
     turn
    0.49
    unno
    0.49
    invokeLater
    0.48
    obacz
    0.47
     Descrip
    0.47
    Activations Density 2.676%

    No Known Activations