© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4844
    Prev
    Next
    INDEX
    Explanations

    instances of the word "stand" and related terms like "shelf" or "sink" where placement of items or objects is discussed, including possible mentions of rules, jobs, or activities.

    oai_token-act-pair · gemini-2.0-flash

    rooms in a house

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    țul
    -0.56
    raeli
    -0.55
     Waray
    -0.55
     letti
    -0.54
    ViewFeatures
    -0.54
    utriche
    -0.52
    Rohy
    -0.51
     hoek
    -0.50
    HasAnnotation
    -0.50
    anair
    -0.49
    POSITIVE LOGITS
    antMatchers
    0.58
    IContainer
    0.54
     AssemblyTitle
    0.54
     बजाय
    0.50
    Datuak
    0.49
    XmlAccessType
    0.48
    /*
    0.47
     onItemClick
    0.46
    searchBar
    0.44
     StatefulWidget
    0.43
    Activations Density 17.266%

    No Known Activations