© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12586
    Prev
    Next
    INDEX
    Explanations

    words and phrases appearing in scientific or technical documents, especially references to figures, tables, and equations

    oai_token-act-pair · gemini-2.0-flash

    for

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
    AndEndTag
    -1.01
    IsPostBack
    -0.95
     ſte
    -0.84
     '\\;'
    -0.83
    ſelf
    -0.82
    ########.
    -0.82
     שוליים
    -0.80
     يتيمه
    -0.80
     Administrativna
    -0.79
     Италијани
    -0.79
    POSITIVE LOGITS
     for
    2.02
    for
    1.30
     для
    1.23
     für
    1.23
     voor
    1.15
     untuk
    1.12
     For
    1.05
     FOR
    1.03
     برای
    0.97
     dla
    0.97
    Activations Density 6.124%

    No Known Activations