© 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. 4252
    Prev
    Next
    INDEX
    Explanations

    aspects of creating something with die cut images, and HTML source code including tables and divs.

    oai_token-act-pair · gemini-2.0-flash

    HTML tables and cutting

    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
    vein
    -0.52
    andalf
    -0.52
     gradient
    -0.51
    mental
    -0.49
     FetchType
    -0.49
     Rings
    -0.49
    loos
    -0.49
    ("="
    -0.48
     gradients
    -0.48
    ecap
    -0.48
    POSITIVE LOGITS
     mergeFrom
    0.60
     addSubview
    0.56
    ConstraintMaker
    0.55
    RectF
    0.52
    جغرافيا
    0.51
    脚注の使い方
    0.49
    etton
    0.49
     AP
    0.49
    ClientRect
    0.48
    RegistryLite
    0.48
    Activations Density 2.042%

    No Known Activations