© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9924
    Prev
    Next
    INDEX
    Explanations

    a specific scientific and technical language usage.

    oai_token-act-pair · gemini-2.0-flash

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     transfieras
    -0.62
    ">//
    -0.56
    تفصیلات
    -0.53
    GGI
    -0.48
    "${
    -0.46
    بوابة
    -0.45
     />";
    -0.42
    clyde
    -0.42
     JADX
    -0.42
    StringLiteral
    -0.41
    POSITIVE LOGITS
    ⓧ
    0.77
    featureID
    0.70
     înc
    0.68
     مرئيه
    0.66
    ativement
    0.66
    ImageContext
    0.65
    writeFieldEnd
    0.64
    DoubleQuotes
    0.57
     decât
    0.57
     frukt
    0.57
    Activations Density 5.584%

    No Known Activations