© 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. 6569
    Prev
    Next
    INDEX
    Explanations

    python code keywords and function definitions

    oai_token-act-pair · gemini-2.0-flash

    programming syntax and keywords

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

    if

    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
     ་་
    -0.88
     Reſ
    -0.88
     myſelf
    -0.82
     itſelf
    -0.82
     Anſ
    -0.81
     ſever
    -0.81
    ſelves
    -0.77
     raiſ
    -0.74
     Diſ
    -0.73
     ―――――
    -0.73
    POSITIVE LOGITS
    .~(\
    0.80
    CRIPTION
    0.72
    ecutive
    0.71
    tourism
    0.69
    landet
    0.68
    CUSSION
    0.67
    aquarium
    0.66
    rítica
    0.66
    quirrel
    0.64
    degenerate
    0.64
    Activations Density 1.054%

    No Known Activations