© 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. 9910
    Prev
    Next
    INDEX
    Explanations

    the word "most" and words near it

    oai_token-act-pair · gemini-2.0-flash

    most

    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
     more
    -0.66
    More
    -0.49
     nakalista
    -0.47
    SuppressMessage
    -0.47
    úsqueda
    -0.47
    ClientSize
    -0.46
     мәкал
    -0.46
    liches
    -0.46
    ucksack
    -0.46
    SourceChecksum
    -0.45
    POSITIVE LOGITS
    帖最后由
    0.68
    Бележки
    0.59
     recognized
    0.57
     seyn
    0.57
     uſed
    0.57
     overridden
    0.56
     بيها
    0.54
     strictest
    0.54
    jmniej
    0.53
    Datuak
    0.53
    Activations Density 2.268%

    No Known Activations