© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9955
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "year"

    oai_token-act-pair · gemini-2.0-flash

    Year

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    York
    -0.88
    YORK
    -0.85
     York
    -0.78
    NameInMap
    -0.72
    DoubleQuotes
    -0.69
     Yunus
    -0.66
    はじめに
    -0.66
     Rowling
    -0.65
    york
    -0.65
    nios
    -0.65
    POSITIVE LOGITS
     NY
    0.61
     Brooklyn
    0.54
     NYC
    0.54
     brus
    0.51
    prefixer
    0.50
     NYPD
    0.48
    NY
    0.48
    午前
    0.47
    ニューヨーク
    0.47
    ąp
    0.46
    Activations Density 0.105%

    No Known Activations