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. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1205
    Prev
    Next
    INDEX
    Explanations

    technical computer code and language markers

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    ंदीखरीदारी
    -1.09
    ValueStyle
    -0.90
    CodeAttribute
    -0.84
     Савезне
    -0.83
    saraba
    -0.83
     linkovi
    -0.80
     disambiguazione
    -0.79
    Vidite
    -0.78
     ویکی‌پدی
    -0.76
     ")");
    -0.76
    POSITIVE LOGITS
    AndEndTag
    0.49
    NOPQRST
    0.47
     MainAxisSize
    0.45
     Bureau
    0.45
     Sari
    0.44
     Mim
    0.44
    LLocation
    0.44
     son
    0.43
     gọn
    0.42
    spo
    0.42
    Activations Density 2.970%

    No Known Activations