© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10941
    Prev
    Next
    INDEX
    Explanations

    This neuron seems to be triggered by a variety of contexts including names, dates, article titles, and events happening over a few days

    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_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     week
    -1.63
     weeks
    -1.56
    week
    -1.48
     months
    -1.42
    weeks
    -1.41
    Week
    -1.39
     Week
    -1.34
     Weeks
    -1.34
    Weeks
    -1.30
     WEEK
    -1.28
    POSITIVE LOGITS
     surla
    0.68
    ArgsConstructor
    0.68
    logous
    0.53
    AndroidJUnit
    0.51
     Fath
    0.50
    rimer
    0.50
     HSS
    0.49
     BeautifulSoup
    0.48
    glVertex
    0.48
    DataSnapshot
    0.47
    Activations Density 6.597%

    No Known Activations