© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 24-GEMMASCOPE-TRANSCODER-16K
    7. 2472
    Prev
    Next
    INDEX
    Explanations

    the word "the" and words that occur frequently with "the", like city names, and adjectives

    oai_token-act-pair · gemini-2.0-flash

    the

    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
     contextLoads
    -0.66
     ExecuteAsync
    -0.66
     disambiguazione
    -0.63
    ']],
    -0.56
    ArrowToggle
    -0.56
    )?;
    -0.56
    )=>{
    -0.55
     Extragalactic
    -0.54
     ostavi
    -0.53
     SqlParameter
    -0.53
    POSITIVE LOGITS
     vidare
    0.48
     noDo
    0.48
    twimg
    0.47
    interopRequire
    0.43
     videre
    0.43
     area
    0.41
    Further
    0.41
     épis
    0.41
     They
    0.40
    guió
    0.40
    Activations Density 1.253%

    No Known Activations