© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13641
    Prev
    Next
    INDEX
    Explanations

    code and code-related terms like "format", "return", "print", and special characters

    oai_token-act-pair · gemini-2.0-flash

    Code snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    tvguidetime
    -1.31
     ―――――
    -1.16
     nahilalakip
    -1.14
    脚注の使い方
    -1.11
     itſelf
    -1.10
     myſelf
    -1.10
    ValueStyle
    -1.09
     purpoſe
    -1.09
     iſt
    -1.05
     ویکی‌پدیای
    -1.05
    POSITIVE LOGITS
     "
    0.58
     
    0.57
     '
    0.57
     “
    0.56
     or
    0.48
     ‘
    0.47
     a
    0.46
    ,
    0.46
    <eos>
    0.46
    “
    0.45
    Activations Density 0.212%

    No Known Activations