© 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. 3333
    Prev
    Next
    INDEX
    Explanations

    words or phrases describing a process of some kind as in manufacturing, computers or electronics

    oai_token-act-pair · gemini-2.0-flash

    processes, beginnings

    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
    waitKey
    -0.78
    awaiter
    -0.67
     transfieras
    -0.64
    SBATCH
    -0.63
    PostMapping
    -0.63
    ServiceModel
    -0.60
    getRuntime
    -0.57
    LookAnd
    -0.56
    msgSender
    -0.55
    WindowEvent
    -0.55
    POSITIVE LOGITS
     löyty
    0.60
    AntiForgeryToken
    0.59
     olev
    0.55
     wyma
    0.54
     tebal
    0.50
    PRNewswire
    0.50
    izacao
    0.48
     deepest
    0.48
     weighs
    0.48
    tachten
    0.48
    Activations Density 10.151%

    No Known Activations