© 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. 15902
    Prev
    Next
    INDEX
    Explanations

    references to a long time period, specifically "for" + a time duration

    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
     years
    -1.69
     Years
    -1.44
     decades
    -1.44
    Years
    -1.42
    years
    -1.38
     YEARS
    -1.38
     decade
    -1.31
     months
    -1.28
    YEARS
    -1.24
     años
    -1.13
    POSITIVE LOGITS
    de
    0.63
    الحياه
    0.50
    stateProvider
    0.49
    र्च
    0.49
     delu
    0.48
    eru
    0.48
    odzi
    0.46
    yarnpkg
    0.45
    ParallelGroup
    0.45
    timo
    0.44
    Activations Density 7.295%

    No Known Activations