© 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
    2. Gemma-2-2B
    3. 19-GEMMASCOPE-TRANSCODER-16K
    4. 6673
    Prev
    Next
    INDEX
    Explanations

    code snippets including parentheses and certain symbols

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    .
    -0.86
    ,
    -0.76
    ↵↵
    -0.74
     the
    -0.73
     
    -0.69
    !
    -0.69
     a
    -0.67
    -
    -0.67
    ↵
    -0.64
    <eos>
    -0.62
    POSITIVE LOGITS
     AssemblyCulture
    1.38
     propOrder
    1.35
     للمعارف
    1.34
    ThroughAttribute
    1.34
    AddTagHelper
    1.31
     المعيارى
    1.28
    ConstraintMaker
    1.27
    IntoConstraints
    1.26
    RenderAtEndOf
    1.24
    endphp
    1.23
    Activations Density 0.959%

    No Known Activations