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. 14382
    Prev
    Next
    INDEX
    Explanations

    words related to actions and descriptions of events

    oai_token-act-pair · gemini-2.0-flash

    Attribution

    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
    enumi
    -0.93
    DockStyle
    -0.86
     Chwiliwch
    -0.85
    RTEX
    -0.82
    InjectAttribute
    -0.82
     дописавши
    -0.82
    ThroughAttribute
    -0.82
    webElementXpaths
    -0.81
    InputBorder
    -0.79
    RenderAtEndOf
    -0.77
    POSITIVE LOGITS
     by
    2.28
     oleh
    1.70
    by
    1.45
     By
    1.32
     توسط
    1.27
    By
    1.23
     ידי
    1.15
     pelos
    1.03
     BY
    1.01
     przez
    1.01
    Activations Density 1.733%

    No Known Activations