© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 5125
    Prev
    Next
    INDEX
    Explanations

    non-alphanumeric characters used for formatting, as well as some words within code

    oai_token-act-pair · gemini-2.0-flash

    Code/Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
    __(/*!
    -0.83
    fromnode
    -0.82
    bootstrapcdn
    -0.79
    ReusableCell
    -0.71
     EconPapers
    -0.68
     Sensi
    -0.68
    HtmlAttribute
    -0.67
         
    -0.67
    Tembelea
    -0.66
     Aner
    -0.65
    POSITIVE LOGITS
    <bos>
    1.66
    ↵
    0.56
    ↵↵
    0.55
    '
    0.53
     the
    0.52
     
    0.51
     we
    0.50
     b
    0.46
    CodeAnalysis
    0.45
     t
    0.43
    Activations Density 0.869%

    No Known Activations