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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 183
    Prev
    Next
    INDEX
    Explanations

    numerical counts of people or things

    oai_token-act-pair · gemini-2.0-flash

    numbers

    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
     dozen
    -0.56
     two
    -0.50
     four
    -0.49
     three
    -0.47
     many
    -0.47
     number
    -0.45
     numerous
    -0.44
     few
    -0.44
     total
    -0.43
     action
    -0.43
    POSITIVE LOGITS
     يتيمه
    0.88
     للمعارف
    0.82
    setVerticalGroup
    0.75
     själva
    0.75
    NameInMap
    0.72
    يكب
    0.71
    IntoConstraints
    0.70
     Pristupljeno
    0.70
    PhysRevLett
    0.66
    PreferredItem
    0.66
    Activations Density 3.563%

    No Known Activations