© 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. 2543
    Prev
    Next
    INDEX
    Explanations

    phrases containing "to", "don't", "or", "a", and contractions ending in 't.

    oai_token-act-pair · gemini-2.0-flash

    to/t

    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
     BoxFit
    -0.73
    yarnpkg
    -0.67
    ThroughAttribute
    -0.66
    AntiForgeryToken
    -0.64
     $_"
    -0.64
    Rhestr
    -0.62
    "){
    -0.62
    .";
    -0.61
     nonatomic
    -0.61
    IsContent
    -0.60
    POSITIVE LOGITS
    airbnb
    0.46
    pheus
    0.45
     inteligen
    0.44
    lid
    0.43
     rá
    0.43
     diable
    0.43
    drage
    0.42
     stre
    0.41
     homemaker
    0.41
     bombard
    0.41
    Activations Density 2.807%

    No Known Activations