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. 1015
    Prev
    Next
    INDEX
    Explanations

    words related to business and technology

    oai_token-act-pair · gemini-2.0-flash

    Business and technology contexts

    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
     Boost
    -0.47
    Mengapa
    -0.46
     plus
    -0.46
     ग्राहक
    -0.46
    vlád
    -0.44
    YesNo
    -0.44
    ",{
    -0.44
     đương
    -0.43
    scriptcase
    -0.43
    ...',
    -0.43
    POSITIVE LOGITS
     snippetHide
    0.66
     ErrIntOverflow
    0.62
    #+#
    0.61
    expandindo
    0.60
     pinulongan
    0.60
    NamedQueries
    0.60
     estekak
    0.59
    Personensuche
    0.58
     poffe
    0.58
     >=",
    0.57
    Activations Density 7.838%

    No Known Activations