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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14202
    Prev
    Next
    INDEX
    Explanations

    javascript code related to testing whether something is a function

    oai_token-act-pair · gemini-2.0-flash

    punctuation

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    Искәрмәләр
    -0.52
    ยก
    -0.46
     ",";
    -0.44
    ials
    -0.44
     ...
    -0.43
    persion
    -0.42
    อ้างอิง
    -0.41
    <?
    -0.41
    ьо
    -0.40
     //$
    -0.40
    POSITIVE LOGITS
    AddTagHelper
    1.04
    IntoConstraints
    0.90
     للاسماء
    0.83
    TagMode
    0.82
     ſche
    0.80
    RenderAtEndOf
    0.79
    DockStyle
    0.78
    styleType
    0.75
    SourceChecksum
    0.75
    <unused79>
    0.73
    Activations Density 6.558%

    No Known Activations