© 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. 23-GEMMASCOPE-TRANSCODER-16K
    7. 11561
    Prev
    Next
    INDEX
    Explanations

    references to technology, purchasing, and GPS in a business context and references to geological forces and elements in a natural context.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_23/width_16k/average_l0_25
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.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
    InOut
    -0.59
     bpy
    -0.57
    gó
    -0.55
    성
    -0.55
    ionView
    -0.54
    ther
    -0.53
    참고
    -0.53
     thermal
    -0.53
     Sinon
    -0.52
    apimachinery
    -0.52
    POSITIVE LOGITS
    ItemBackground
    0.73
     насељу
    0.72
    AndEndTag
    0.69
     linkovi
    0.61
    ValueStyle
    0.60
    InitVars
    0.57
    addGap
    0.52
    Personensuche
    0.49
    JpaRepository
    0.49
    isContained
    0.49
    Activations Density 3.110%

    No Known Activations