© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 11636
    Prev
    Next
    INDEX
    Explanations

    words related to history, politics, legal matters and biographical narrative and personal evaluation

    oai_token-act-pair · gemini-2.0-flash

    French words

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     budgets
    -1.09
     charters
    -0.98
     '\\;'
    -0.96
    存于互联网档案馆
    -0.95
     catalogs
    -0.94
     portfolios
    -0.90
     Bibles
    -0.90
     Budgets
    -0.89
    UnsafeEnabled
    -0.88
     catalogues
    -0.87
    POSITIVE LOGITS
     épaules
    0.54
     renseignements
    0.46
     seres
    0.44
     bienfaits
    0.43
     critères
    0.43
     modalités
    0.43
     ingrédients
    0.40
     attentes
    0.40
     strán
    0.40
    doe
    0.40
    Activations Density 9.771%

    No Known Activations