© 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. 25-GEMMASCOPE-TRANSCODER-16K
    7. 4447
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific notations and symbols, with a particular emphasis on "COX" and "STAT" and a lesser emphasis on "IFN"

    oai_token-act-pair · gemini-2.0-flash

    technical language

    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
    four
    -0.68
    4
    -0.67
    5
    -0.64
    Four
    -0.63
     Four
    -0.62
     four
    -0.61
    five
    -0.61
     Fünf
    -0.61
    Five
    -0.58
    8
    -0.58
    POSITIVE LOGITS
     ModelExpression
    1.02
    تقاوى
    0.95
    دانشنامهٔ
    0.87
    +#+
    0.84
    urlpatterns
    0.83
     للاسماء
    0.83
     surla
    0.81
    bootstrapcdn
    0.80
    Билгалдахарш
    0.78
    XmlEnum
    0.77
    Activations Density 1.225%

    No Known Activations