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. 1150
    Prev
    Next
    INDEX
    Explanations

    a wide variety of seemingly unrelated symbols and phrases, including mathematical symbols, website URLs, and the phrase "first things".

    oai_token-act-pair · gemini-2.0-flash

    code snippets and tweets

    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
     Púb
    -0.51
     fusca
    -0.48
    okovic
    -0.48
     PLWABN
    -0.48
     crudo
    -0.47
    ladolid
    -0.47
     frito
    -0.45
    بوك
    -0.45
     Outils
    -0.44
     tiros
    -0.44
    POSITIVE LOGITS
    Personensuche
    0.87
     CreateTagHelper
    0.78
    webElementGuid
    0.76
    BeginContext
    0.75
     فريبيس
    0.72
    ]='\
    0.72
     يتيمه
    0.70
     estekak
    0.69
    kháu
    0.67
    IntoConstraints
    0.67
    Activations Density 1.651%

    No Known Activations