© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 9810
    Prev
    Next
    INDEX
    Explanations

    mentions of months or dates in reference to people

    oai_token-act-pair · gemini-2.0-flash

    months

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.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
    GOTREF
    -0.57
     Meksiku
    -0.56
     onPage
    -0.49
    mares
    -0.49
    раздо
    -0.48
     GetEnumerator
    -0.45
    ftagPool
    -0.44
     Kuma
    -0.43
    anyway
    -0.43
    zus
    -0.42
    POSITIVE LOGITS
     الرياضيه
    0.68
     päivä
    0.67
     étoient
    0.61
     universale
    0.60
     Romains
    0.60
     męski
    0.60
    ItemBackground
    0.59
    yanka
    0.58
    kolwiek
    0.57
     eccl
    0.57
    Activations Density 0.210%

    No Known Activations