© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6288
    Prev
    Next
    INDEX
    Explanations

    this neuron detects programming code, or at least the symbols and keywords commonly used in programming

    oai_token-act-pair · gemini-2.0-flash

    Code and college team names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     itſelf
    -1.36
     Jefus
    -1.30
    ſelves
    -1.29
     Theſe
    -1.29
    ſelf
    -1.28
     Houſe
    -1.27
     Majefty
    -1.25
     $_"
    -1.22
     myſelf
    -1.20
     Efq
    -1.18
    POSITIVE LOGITS
    ,
    0.93
    .
    0.90
    :
    0.81
    ↵
    0.77
    !
    0.77
    (
    0.76
     (
    0.73
     "
    0.71
    ;
    0.70
    <eos>
    0.68
    Activations Density 0.322%

    No Known Activations