Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13439
    Prev
    Next
    INDEX
    Explanations

    hexadecimal or numerical codes

    oai_token-act-pair · gemini-2.0-flash

    xc

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     Stol
    -0.58
    Bromoform
    -0.57
    <0xA4>
    -0.55
     спо
    -0.51
     Spartans
    -0.49
    isNotBlank
    -0.48
    $__
    -0.46
    zon
    -0.46
    Спо
    -0.45
    amma
    -0.45
    POSITIVE LOGITS
    Datuak
    1.08
     تضيفلها
    0.96
     InputDecoration
    0.79
     kasarigan
    0.74
    ArrowToggle
    0.73
    MLLoader
    0.72
     ModelExpression
    0.71
    CodedInputStream
    0.71
    parsedMessage
    0.69
    Билгалдахарш
    0.69
    Activations Density 3.789%

    No Known Activations