© 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. 13224
    Prev
    Next
    INDEX
    Explanations

    angle brackets and the words "content", "div", hyphens, and equals signs, all characteristics of HTML code

    oai_token-act-pair · gemini-2.0-flash

    <

    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
     initComponents
    -0.65
    itano
    -0.54
     nine
    -0.48
    IRED
    -0.46
     an
    -0.46
     Sha
    -0.46
     Text
    -0.45
     new
    -0.45
     المر
    -0.44
     tea
    -0.44
    POSITIVE LOGITS
    RenderAtEndOf
    0.80
     Shakspeare
    0.77
    PYX
    0.75
    脚注の使い方
    0.70
    AsUp
    0.70
     jupiter
    0.69
    Zed
    0.68
    PreferredItem
    0.67
    XmlAccessType
    0.67
    новниш
    0.67
    Activations Density 0.402%

    No Known Activations