© 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. 24-GEMMASCOPE-TRANSCODER-16K
    7. 7592
    Prev
    Next
    INDEX
    Explanations

    architects and museums, especially when an architect is designing the building

    oai_token-act-pair · gemini-2.0-flash

    Architecture and design

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_24/width_16k/average_l0_37
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.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
     pinulongan
    -0.86
     للاسماء
    -0.81
    DockStyle
    -0.73
    клопе
    -0.73
     مرئيه
    -0.71
     GreatSchools
    -0.68
    例句
    -0.68
    Sucesor
    -0.68
     समीक्षाओं
    -0.67
    SourceChecksum
    -0.66
    POSITIVE LOGITS
     Silent
    0.48
     Donnelly
    0.46
     Ok
    0.44
     cib
    0.44
    silent
    0.43
     en
    0.43
     oport
    0.42
     doble
    0.41
    anom
    0.41
    ecia
    0.41
    Activations Density 2.132%

    No Known Activations