© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16051
    Prev
    Next
    INDEX
    Explanations

    angle brackets and semicolons that are used in XML like computer code

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    __":
    -0.85
    $.
    -0.82
    __':
    -0.76
    )";
    -0.71
    _
    -0.71
    "?>
    -0.69
    "),
    -0.69
    "]];
    -0.69
    "],
    -0.69
    ")){
    -0.68
    POSITIVE LOGITS
    <bos>
    0.80
    abestanden
    0.71
    Vidite
    0.67
     AssemblyCulture
    0.66
     Италијани
    0.64
    SourceChecksum
    0.64
    MergeFrom
    0.62
     ostavi
    0.59
     архивлан
    0.59
    WireFormatLite
    0.58
    Activations Density 4.154%

    No Known Activations