© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 4935
    Prev
    Next
    INDEX
    Explanations

    mentions of years and amounts of time

    oai_token-act-pair · gemini-2.0-flash

    year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     three
    -0.72
     four
    -0.61
    three
    -0.58
    Three
    -0.56
     trois
    -0.56
     THREE
    -0.55
     fyra
    -0.54
     drie
    -0.53
     Three
    -0.53
     five
    -0.52
    POSITIVE LOGITS
     year
    1.16
    year
    1.11
     Year
    1.06
     annually
    1.03
    Year
    1.01
     yearly
    0.96
    YEAR
    0.96
     jaar
    0.96
     annual
    0.95
     YEAR
    0.95
    Activations Density 1.295%

    No Known Activations