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. 13674
    Prev
    Next
    INDEX
    Explanations

    code snippets and category names, especially from technical documents

    oai_token-act-pair · gemini-2.0-flash

    Technical documentation and code

    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
    年
    -1.06
    년
    -0.73
     年
    -0.59
    月
    -0.52
     thicker
    -0.50
    ynb
    -0.50
    withIdentifier
    -0.50
     thicken
    -0.49
    InputTagHelper
    -0.47
     упро
    -0.47
    POSITIVE LOGITS
    <bos>
    0.98
    RegistryLite
    0.73
     चीज़ों
    0.72
    ValueStyle
    0.68
    Билгалдахарш
    0.58
     autorytatywna
    0.56
    रीदारी
    0.55
     picked
    0.55
    contentLoaded
    0.54
     BoxDecoration
    0.54
    Activations Density 10.079%

    No Known Activations