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. 0-GEMMASCOPE-TRANSCODER-16K
    4. 7277
    Prev
    Next
    INDEX
    Explanations

    vertical divider symbols and keywords like "array", and other function words near relevant symbols

    oai_token-act-pair · gemini-2.0-flash

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.85
     Efq
    -1.46
     myſelf
    -1.41
     Monfieur
    -1.39
     itſelf
    -1.38
     Theſe
    -1.33
     Jefus
    -1.23
     Majefty
    -1.22
     himſelf
    -1.21
     themſelves
    -1.21
    POSITIVE LOGITS
    <eos>
    0.77
     _
    0.68
     [
    0.68
     –
    0.68
     B
    0.65
     (
    0.65
    fa
    0.63
     R
    0.63
     F
    0.63
    ma
    0.62
    Activations Density 2.745%

    No Known Activations