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. 19-GEMMASCOPE-TRANSCODER-16K
    4. 9975
    Prev
    Next
    INDEX
    Explanations

    words related to competitions and winners

    oai_token-act-pair · gemini-2.0-flash

    winner

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
    icrous
    -0.61
    uroy
    -0.59
    AllAfrica
    -0.58
    ThroughAttribute
    -0.58
    findpost
    -0.57
    ابراین
    -0.57
    #+#
    -0.54
     /\.(
    -0.54
     Rel
    -0.53
    }}]{
    -0.53
    POSITIVE LOGITS
    classnames
    0.57
     unknown
    0.54
     identified
    0.52
     Identified
    0.51
    AddTagHelper
    0.50
    lapsingToolbar
    0.50
     <<<<<<<<<<<<<<
    0.48
     تضيفلها
    0.48
    thâu
    0.48
    Identified
    0.48
    Activations Density 2.809%

    No Known Activations