© 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. 4454
    Prev
    Next
    INDEX
    Explanations

    words used in technical documentation or posts, often related to computer programming, debugging, or medical tests

    oai_token-act-pair · gemini-2.0-flash

    programming related texts

    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
     hänen
    -0.60
    Viitteet
    -0.59
     elä
    -0.54
     mør
    -0.54
     genoux
    -0.53
     aydın
    -0.53
     figliu
    -0.52
     morire
    -0.50
     sogni
    -0.49
     társ
    -0.49
    POSITIVE LOGITS
    ⓧ
    0.73
     AssemblyCulture
    0.69
    حياته
    0.69
     bef
    0.67
     inf
    0.67
     ar
    0.66
    PyExc
    0.66
    </i>
    0.65
     int
    0.64
     fr
    0.64
    Activations Density 5.128%

    No Known Activations