© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 14895
    Prev
    Next
    INDEX
    Explanations

    computer-server and software development related terms

    oai_token-act-pair · gemini-2.0-flash

    field

    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
     propOrder
    -0.75
    iprot
    -0.61
    onOptions
    -0.56
    acular
    -0.56
     Halley
    -0.55
    GraphicsUnit
    -0.55
    ochond
    -0.52
     Holstein
    -0.52
     symbols
    -0.50
     **)
    -0.50
    POSITIVE LOGITS
     field
    0.60
    Field
    0.60
    #![
    0.59
    field
    0.57
     control
    0.56
    control
    0.49
     Field
    0.49
     поле
    0.48
     fréqu
    0.47
    FieldNumber
    0.47
    Activations Density 6.896%

    No Known Activations