© 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. 18-GEMMASCOPE-TRANSCODER-16K
    7. 4856
    Prev
    Next
    INDEX
    Explanations

    technical vocabularly or phrases associated with experimental procedures or setups.

    oai_token-act-pair · gemini-2.0-flash

    scientific processes/tools

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
    */].
    -0.50
     camar
    -0.50
     mon
    -0.48
     وتسجيلات
    -0.48
    HAI
    -0.48
    ouse
    -0.47
    ILERS
    -0.47
    siede
    -0.47
    GTCX
    -0.45
     hard
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.78
     ComVisible
    0.60
    SharedDtor
    0.59
     inalámb
    0.57
    CreateModel
    0.57
     initComponents
    0.54
    出版年
    0.54
     enfans
    0.54
     MainAxisSize
    0.53
    ScopeManager
    0.52
    Activations Density 18.016%

    No Known Activations