© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 6273
    Prev
    Next
    INDEX
    Explanations

    the word "artificial"

    oai_token-act-pair · gemini-2.0-flash

    artificial

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
     Salve
    -0.66
     deference
    -0.65
     Specialization
    -0.64
     sovereigns
    -0.63
     sorption
    -0.63
     CMB
    -0.63
    n
    -0.62
     photosynthesis
    -0.62
    ma
    -0.62
     Hemisphere
    -0.60
    POSITIVE LOGITS
     nahilalakip
    1.00
    ſhip
    0.97
     ویکی‌پدیا
    0.90
    PyExc
    0.88
    BibitemShut
    0.88
    eſt
    0.86
     }}$}
    0.84
     فريبيس
    0.82
    NSNotification
    0.81
    leſs
    0.81
    Activations Density 0.999%

    No Known Activations