© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 25-GEMMASCOPE-TRANSCODER-16K
    7. 10247
    Prev
    Next
    INDEX
    Explanations

    words and phrases that are often used in programming and mathematics, or that describe established coding practices

    oai_token-act-pair · gemini-2.0-flash

    technical contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.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
     always
    -2.98
    always
    -2.84
    Always
    -2.72
     Always
    -2.70
     siempre
    -2.52
     sempre
    -2.47
     ALWAYS
    -2.20
    siempre
    -2.17
     всегда
    -2.16
    sempre
    -2.16
    POSITIVE LOGITS
    setupUi
    0.53
    gdx
    0.50
    PropertyChanging
    0.50
    เหลือ
    0.49
     Nema
    0.47
    Initializable
    0.47
    onez
    0.47
    fecture
    0.46
    databind
    0.46
     HttpNotFound
    0.45
    Activations Density 5.515%

    No Known Activations