© 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. 10340
    Prev
    Next
    INDEX
    Explanations

    mentions of women of childbearing age

    oai_token-act-pair · gemini-2.0-flash

    activities involving 'childbearing'

    np_token-act-pair-logits · gpt-4o-mini
    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
    NameInMap
    -0.68
    +#+#
    -0.60
     незавершена
    -0.56
     arşivlendi
    -0.55
    aspectj
    -0.54
    gridx
    -0.53
    Réalisation
    -0.50
    routeProvider
    -0.50
     للمعارف
    -0.49
    حياته
    -0.49
    POSITIVE LOGITS
     negotiating
    0.87
     drinking
    0.81
     voting
    0.80
     punching
    0.79
     policing
    0.78
     pitching
    0.77
     firing
    0.77
     cooking
    0.77
     plotting
    0.75
     cleaning
    0.75
    Activations Density 2.601%

    No Known Activations