© 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. 12902
    Prev
    Next
    INDEX
    Explanations

    words, abbreviations, and symbols related to scientific and technical writing with a focus on research.

    oai_token-act-pair · gemini-2.0-flash

    scientific and technical data

    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
     fishery
    -0.68
     ComVisible
    -0.66
    Tikang
    -0.66
     sī
    -0.65
    WebKit
    -0.64
     game
    -0.62
     statements
    -0.62
     panels
    -0.60
     Krankheit
    -0.60
    game
    -0.59
    POSITIVE LOGITS
     ostavi
    0.56
     note
    0.52
    Races
    0.51
    merking
    0.48
    
    0.48
     example
    0.48
    Trains
    0.48
    Diseases
    0.47
     report
    0.47
    toISOString
    0.46
    Activations Density 12.288%

    No Known Activations