© 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. 13393
    Prev
    Next
    INDEX
    Explanations

    words related to items, merchandise, and code, and identifiers like INV and IT.

    oai_token-act-pair · gemini-2.0-flash

    data items/articles

    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
    twimg
    -0.66
    ResponseCode
    -0.59
    RenderAtEndOf
    -0.58
     onFailure
    -0.54
    invokeLater
    -0.54
    Бахар
    -0.52
     Gier
    -0.52
     stumped
    -0.52
    nsf
    -0.52
    uteurs
    -0.51
    POSITIVE LOGITS
     ModelExpression
    0.68
    :✨
    0.65
     items
    0.65
     Items
    0.63
     Item
    0.59
     Merchandise
    0.58
     merchandise
    0.57
     يتيمه
    0.57
     item
    0.56
     objects
    0.56
    Activations Density 1.184%

    No Known Activations