© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 15712
    Prev
    Next
    INDEX
    Explanations

    place names, chemical elements, medical and political terms

    oai_token-act-pair · gemini-2.0-flash

    Locations and chemical elements

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
     myſelf
    -0.62
    TagHelper
    -0.59
    tagena
    -0.58
     ſever
    -0.57
     ſeveral
    -0.55
     ſhe
    -0.55
     Conſ
    -0.54
     Jefus
    -0.53
    ſelves
    -0.52
     Perſ
    -0.52
    POSITIVE LOGITS
    InjectAttribute
    0.86
    脚注の使い方
    0.74
    setVerticalGroup
    0.73
    UnusedPrivate
    0.70
    WebElementEntity
    0.69
    MigrationBuilder
    0.61
    awtextra
    0.59
     oprot
    0.55
    Rüyada
    0.54
    цезда
    0.54
    Activations Density 3.933%

    No Known Activations