© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 22-GEMMASCOPE-TRANSCODER-16K
    7. 2868
    Prev
    Next
    INDEX
    Explanations

    restaurant or cafe reviews giving opinions and descriptions of the location and food.

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     E
    -0.63
     his
    -0.62
     B
    -0.59
     |
    -0.58
     
    -0.57
     (
    -0.56
     D
    -0.56
    .
    -0.56
     a
    -0.55
     is
    -0.55
    POSITIVE LOGITS
    RenderAtEndOf
    1.16
     AssemblyTitle
    1.10
     propOrder
    1.07
    ItemBackground
    1.03
     Efq
    1.02
    GEBURTSDATUM
    1.02
    webElementXpaths
    1.01
    makeConstraints
    1.01
    OGND
    0.96
     kaarangay
    0.95
    Activations Density 1.327%

    No Known Activations