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. 683
    Prev
    Next
    INDEX
    Explanations

    statistical data including percentages, numerical values, and associated words like population or cosmology

    oai_token-act-pair · gemini-2.0-flash

    data and statistics

    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
    findpost
    -0.80
    AutoScale
    -0.64
    AccessorTable
    -0.63
     متعلقه
    -0.61
    TestBed
    -0.60
    WebVitals
    -0.60
     curieux
    -0.59
    iecie
    -0.59
    
    -0.58
    RTDA
    -0.57
    POSITIVE LOGITS
     percent
    0.61
     percentage
    0.59
    olume
    0.56
     percentages
    0.54
    percent
    0.54
    百分
    0.53
     (%)
    0.53
    حياتها
    0.53
     Percent
    0.52
     Percentage
    0.52
    Activations Density 2.104%

    No Known Activations