© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 3657
    Prev
    Next
    INDEX
    Explanations

    terms related to HTML display properties and graduation ceremonies.

    oai_token-act-pair · gemini-2.0-flash

    display

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     display
    -2.59
     Display
    -2.44
    Display
    -2.39
    display
    -2.39
     displays
    -2.13
     DISPLAY
    -2.06
     displaying
    -1.90
     displayed
    -1.88
     Displays
    -1.80
    DISPLAY
    -1.73
    POSITIVE LOGITS
     AssemblyCulture
    0.60
     UserController
    0.57
     HomeController
    0.56
    Diweddarwch
    0.56
    OptionsMenu
    0.56
    /*++
    0.54
    keyCode
    0.53
    IntoConstraints
    0.53
    MessageOf
    0.52
    ::~
    0.52
    Activations Density 13.821%

    No Known Activations