© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11209
    Prev
    Next
    INDEX
    Explanations

    the word "date" in different contexts, including database entries and calendar references

    oai_token-act-pair · gemini-2.0-flash

    date

    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
     start
    -0.79
    start
    -0.78
    Start
    -0.75
     Start
    -0.70
    getStart
    -0.69
    IntoConstraints
    -0.65
    START
    -0.65
     getStart
    -0.65
     started
    -0.62
     starting
    -0.62
    POSITIVE LOGITS
    oredCriteria
    0.77
     kasarigan
    0.77
    Билгалдахарш
    0.77
    SharedDtor
    0.62
    ništ
    0.59
    Presence
    0.59
    presence
    0.58
     presence
    0.57
     Presence
    0.56
    ODB
    0.55
    Activations Density 3.283%

    No Known Activations