© 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. 6633
    Prev
    Next
    INDEX
    Explanations

    This neuron tries to identify code and numbers

    oai_token-act-pair · gemini-2.0-flash

    file paths or programming terms

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

    Calculation/code output

    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
     nahilalakip
    -0.59
     незавершена
    -0.59
     quelcon
    -0.57
     huit
    -0.57
    Berikut
    -0.54
    ledem
    -0.53
     oito
    -0.52
     eight
    -0.50
     ſeveral
    -0.49
     itſelf
    -0.49
    POSITIVE LOGITS
     "..\..\
    0.54
     utafitiHapana
    0.52
     amp
    0.52
     Hampton
    0.51
    TypedDataSet
    0.51
    InitVars
    0.50
     ویکی‌پدی
    0.49
    исленность
    0.49
     co
    0.49
     "..\..\..\
    0.49
    Activations Density 6.936%

    No Known Activations