© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 11347
    Prev
    Next
    INDEX
    Explanations

    a variety of comparatives, numerical references, mathematical symbols, and what appears to be code.

    oai_token-act-pair · gemini-2.0-flash

    German

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     steeper
    -0.68
     più
    -0.65
     greater
    -0.63
     sharper
    -0.63
     greatest
    -0.62
     sweetest
    -0.62
     hars
    -0.61
     stiffer
    -0.61
     tighter
    -0.60
     worse
    -0.59
    POSITIVE LOGITS
     geslacht
    0.60
     mergeFrom
    0.60
    addCriterion
    0.58
    PostExecute
    0.57
    SourceChecksum
    0.56
    Otras
    0.56
    Geplaatst
    0.56
     Bioaccumulative
    0.55
    Sitemap
    0.55
    Insee
    0.55
    Activations Density 1.704%

    No Known Activations