© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 9967
    Prev
    Next
    INDEX
    Explanations

    numbers and units related to time or quantity in news articles

    oai_token-act-pair · gemini-2.0-flash

    Quantities, distances, time

    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
     estimés
    -0.75
    IntoConstraints
    -0.67
     endblock
    -0.60
    StructEnd
    -0.58
    ScopeManager
    -0.53
     Applies
    -0.53
    WaitGroup
    -0.52
    PerformLayout
    -0.51
    netje
    -0.51
    ParallelGroup
    -0.50
    POSITIVE LOGITS
    AndEndTag
    0.54
    FieldDescriptor
    0.53
     chi̍t
    0.51
     trợ
    0.50
    ITZER
    0.50
     most
    0.48
     nos
    0.47
    МК
    0.47
    nora
    0.47
    cro
    0.47
    Activations Density 2.584%

    No Known Activations