© 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. 12114
    Prev
    Next
    INDEX
    Explanations

    mentions of time duration, including years, decades or a while.

    oai_token-act-pair · gemini-2.0-flash

    Time periods

    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
     resourceCulture
    -0.85
    ViewImports
    -0.80
    SharedCtor
    -0.79
    TagMode
    -0.71
    AccessorTable
    -0.71
    '):
    -0.70
    PhysRevD
    -0.69
    setVerticalGroup
    -0.68
    FTFY
    -0.67
    orous
    -0.67
    POSITIVE LOGITS
     äldre
    0.43
     conséquences
    0.41
     îmb
    0.40
     barbati
    0.40
     élevées
    0.40
    ctest
    0.40
     flesta
    0.39
     superiori
    0.37
     sintomas
    0.36
     muuta
    0.36
    Activations Density 0.661%

    No Known Activations