© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 8452
    Prev
    Next
    INDEX
    Explanations

    fragments of HTML code or special characters often found in programming data

    oai_token-act-pair · gemini-2.0-flash

    HTML header tags

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

    Code and programming

    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
    tably
    -0.52
    AndEndTag
    -0.51
    menti
    -0.48
    ">*</
    -0.48
    tage
    -0.48
    FileDescriptor
    -0.47
    PropertyChanged
    -0.47
    ècie
    -0.46
    Ссылки
    -0.46
     हुए
    -0.46
    POSITIVE LOGITS
    windowFixed
    0.62
     متعلقه
    0.62
    Personensuche
    0.61
     betweenstory
    0.57
    CopyWith
    0.57
    хьтан
    0.56
    TintMode
    0.56
    脚注の使い方
    0.54
    ++){
    0.54
    InjectAttribute
    0.52
    Activations Density 0.046%

    No Known Activations