© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 12458
    Prev
    Next
    INDEX
    Explanations

    words or phrases involving time

    oai_token-act-pair · gemini-2.0-flash

    seasons and periods of time

    np_token-act-pair-logits · gpt-4o-mini

    Seasons

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ylase
    -0.56
    坞
    -0.56
    gheny
    -0.53
    [__
    -0.52
    Selama
    -0.52
    hobia
    -0.49
     Durante
    -0.48
     Schatten
    -0.47
    ниципа
    -0.47
    Jeografia
    -0.47
    POSITIVE LOGITS
     winter
    0.71
    AddHtmlAttribute
    0.70
     autumn
    0.68
     summer
    0.65
     spring
    0.64
     fall
    0.64
    StoryboardSegue
    0.62
    fall
    0.62
     Fall
    0.61
     childhood
    0.60
    Activations Density 2.133%

    No Known Activations