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. 808
    Prev
    Next
    INDEX
    Explanations

    snippets of code, particularly syntax and symbols used in declarations and definitions in various programming languages

    oai_token-act-pair · gemini-2.0-flash

    code

    np_max-act · 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
     NSCoder
    -0.54
    BeginContext
    -0.54
    <?>>
    -0.54
    出版年
    -0.51
    ^(@)
    -0.48
    хьтан
    -0.48
     وتسجيلات
    -0.46
    bove
    -0.46
     traffic
    -0.45
    traffic
    -0.45
    POSITIVE LOGITS
    posedge
    0.60
    íncia
    0.56
     Normdatei
    0.55
    gwin
    0.54
    apunov
    0.51
    ubble
    0.50
    ArrowToggle
    0.50
    entuh
    0.49
    bollah
    0.49
    glide
    0.49
    Activations Density 11.670%

    No Known Activations