© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12637
    Prev
    Next
    INDEX
    Explanations

    mentions of numbers and years together

    oai_token-act-pair · gemini-2.0-flash

    words related to medical terminology and statistics

    np_token-act-pair-logits · gpt-4o-mini

    number of years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
     years
    -0.78
     YEARS
    -0.73
     Years
    -0.72
    years
    -0.70
    Years
    -0.66
     años
    -0.61
    YEARS
    -0.60
     évek
    -0.60
     jaren
    -0.59
     anos
    -0.56
    POSITIVE LOGITS
    verwijspagina
    0.71
     تضيفلها
    0.67
     betweenstory
    0.64
    HostException
    0.60
    ########.
    0.58
    COVER
    0.56
     couvert
    0.56
    endpush
    0.56
     resourceCulture
    0.55
     debugger
    0.54
    Activations Density 1.257%

    No Known Activations