© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 12753
    Prev
    Next
    INDEX
    Explanations

    time and seasonal references

    oai_token-act-pair · gemini-2.0-flash

    days and times

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
    ſelf
    -0.83
    ſelves
    -0.78
    Autoritní
    -0.77
     itſelf
    -0.71
    :✨
    -0.71
     myſelf
    -0.69
    ^(@)
    -0.67
    //
    -0.67
     fubject
    -0.66
     scin
    -0.65
    POSITIVE LOGITS
     period
    0.53
     periods
    0.50
     peak
    0.50
    u
    0.48
     esti
    0.48
     times
    0.48
    段
    0.47
    "+
    0.46
    "
    0.45
    Mon
    0.44
    Activations Density 1.275%

    No Known Activations