© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 3708
    Prev
    Next
    INDEX
    Explanations

    sentences or phrases where people discuss their sleep and attempt to manage effects of not sleeping enough.

    oai_token-act-pair · gemini-2.0-flash

    sufficient, enough

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     NSCoder
    -0.71
    "){
    -0.65
    TProtocol
    -0.63
     MessageBoxIcon
    -0.60
    fillType
    -0.59
     ProtoMessage
    -0.57
    '])){
    -0.57
    "]))
    -0.56
    ."],
    -0.56
     AspNetCore
    -0.56
    POSITIVE LOGITS
     drinking
    0.53
     Drinking
    0.50
     plenty
    0.48
     suff
    0.48
     sufficient
    0.48
     adequate
    0.48
    Rujuakan
    0.45
     enough
    0.45
    Drinking
    0.44
     ample
    0.43
    Activations Density 1.474%

    No Known Activations