© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11077
    Prev
    Next
    INDEX
    Explanations

    mentions of time, especially in the context of waiting or length.

    oai_token-act-pair · gemini-2.0-flash

    time units

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     Hour
    -0.85
     hour
    -0.84
     Stunde
    -0.83
     HOUR
    -0.73
    hour
    -0.72
    Hour
    -0.70
    Hours
    -0.69
     часа
    -0.68
     heure
    -0.68
     Hours
    -0.68
    POSITIVE LOGITS
    WithIOException
    0.68
    SourceChecksum
    0.60
    ését
    0.59
    homonymie
    0.56
    RegistryLite
    0.52
    HeaderText
    0.50
    adpleegd
    0.48
    
    0.47
     törvény
    0.47
    ніципалі
    0.47
    Activations Density 11.441%

    No Known Activations