© 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. 5525
    Prev
    Next
    INDEX
    Explanations

    the verb "lay" in various tenses

    oai_token-act-pair · gemini-2.0-flash

    lay

    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
     amitié
    -0.50
    MessageTagHelper
    -0.50
    getSeconds
    -0.49
     étoient
    -0.49
     ouvriers
    -0.48
     المعيارى
    -0.47
     ſec
    -0.47
    dersfield
    -0.47
    OnDelete
    -0.46
     ſet
    -0.46
    POSITIVE LOGITS
    <bos>
    0.64
     ExecuteAsync
    0.59
    TestingModule
    0.56
    PropertyChanging
    0.51
    országban
    0.51
     thick
    0.50
     de
    0.48
     pur
    0.48
    openzeppelin
    0.47
    RectangleBorder
    0.47
    Activations Density 1.145%

    No Known Activations