© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 2414
    Prev
    Next
    INDEX
    Explanations

    words and roman numerals related to people and events in Danish history

    oai_token-act-pair · gemini-2.0-flash

    election

    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
    يمه
    -0.54
    toHaveBeenCalled
    -0.52
     RAND
    -0.50
    fancybox
    -0.49
    nae
    -0.49
    srand
    -0.49
     Employers
    -0.48
    resizeMode
    -0.47
    includegraphics
    -0.47
    ecks
    -0.47
    POSITIVE LOGITS
    Tembelea
    0.62
    PreferredItem
    0.59
    Diweddarwch
    0.59
     GenerationType
    0.57
     Biôgrafia
    0.56
    SourceChecksum
    0.55
    MENAFN
    0.51
     fonder
    0.51
    CppCodeGen
    0.50
    NewRow
    0.50
    Activations Density 2.013%

    No Known Activations