© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 9027
    Prev
    Next
    INDEX
    Explanations

    descriptions of people in a resting state, such as lying down or lying in bed, or in a state of injury, and also some filler words that often occur in sentences describing such situations

    oai_token-act-pair · gemini-2.0-flash

    lay/lying

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     lie
    -1.58
     lies
    -1.45
     lying
    -1.38
     Lying
    -1.20
    Lying
    -1.16
     Lies
    -1.15
    Lie
    -1.14
     Lie
    -1.09
     LIE
    -1.09
     lay
    -1.06
    POSITIVE LOGITS
    DrawerToggle
    0.56
     face
    0.51
    //
    0.50
    ruptedException
    0.47
     belle
    0.47
    bildeten
    0.46
     presencia
    0.45
    ษา
    0.45
    nito
    0.45
     stand
    0.44
    Activations Density 2.273%

    No Known Activations