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. 20-GEMMASCOPE-TRANSCODER-16K
    4. 14526
    Prev
    Next
    INDEX
    Explanations

    references to roads and highways, especially those with route numbers and dates

    oai_token-act-pair · gemini-2.0-flash

    Foreign language text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     препратки
    -0.93
    mybatisplus
    -0.87
    ScopeManager
    -0.81
     houſe
    -0.77
     ſtate
    -0.75
    PhysRevD
    -0.75
    :+:
    -0.73
     surla
    -0.73
     raiſ
    -0.72
     springfox
    -0.71
    POSITIVE LOGITS
    //
    0.36
    лян
    0.35
     di
    0.34
    Arrive
    0.33
    med
    0.33
    Arrival
    0.33
    ca
    0.33
     ngo
    0.33
     فإن
    0.33
     deposited
    0.32
    Activations Density 1.089%

    No Known Activations