© 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. 15016
    Prev
    Next
    INDEX
    Explanations

    mentions of sleep or sleep apnea and its effects.

    oai_token-act-pair · gemini-2.0-flash

    sleep

    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
     night
    -1.05
    night
    -0.94
     Night
    -0.93
     nights
    -0.93
    Night
    -0.91
     NIGHT
    -0.89
     nuit
    -0.83
    nights
    -0.79
     Nights
    -0.79
     nightly
    -0.75
    POSITIVE LOGITS
    stay
    0.67
     stay
    0.66
     staying
    0.65
     Stay
    0.62
     stays
    0.60
    Stay
    0.59
     stayed
    0.58
     STAY
    0.57
    +#+#
    0.56
    stays
    0.53
    Activations Density 1.225%

    No Known Activations