© 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. 11067
    Prev
    Next
    INDEX
    Explanations

    Japanese names and terms, especially those related to a specific series/story.

    oai_token-act-pair · gemini-2.0-flash

    ugi

    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
     transfieras
    -0.71
     Paglinawan
    -0.60
     архивлан
    -0.57
    AddTagHelper
    -0.53
    NOPQRST
    -0.52
    ۇ
    -0.50
    ThroughAttribute
    -0.50
    Erfolge
    -0.50
    colección
    -0.49
     épaules
    -0.49
    POSITIVE LOGITS
    persion
    0.60
     animé
    0.59
    acağı
    0.57
     colonists
    0.57
     calyx
    0.56
     ratification
    0.56
     pokoj
    0.56
     bitters
    0.56
     adjectives
    0.55
     splitter
    0.55
    Activations Density 0.268%

    No Known Activations