© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 7-GEMMASCOPE-TRANSCODER-16K
    7. 10345
    Prev
    Next
    INDEX
    Explanations

    indented or spaced sections in the text

    oai_token-act-pair · gemini-2.0-flash

    Scientific/mathematical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
     retenir
    -0.44
    reuth
    -0.44
     comparison
    -0.41
    Traversal
    -0.41
     Grade
    -0.41
     informé
    -0.40
     inertia
    -0.39
    ruecos
    -0.39
    کلی
    -0.39
    comparison
    -0.38
    POSITIVE LOGITS
     تانيه
    0.73
     autorytatywna
    0.67
     nahilalakip
    0.63
     fathoms
    0.63
    setVerticalGroup
    0.62
     lenker
    0.61
    ponses
    0.60
    PyExc
    0.60
     بيها
    0.59
    WebVitals
    0.59
    Activations Density 0.362%

    No Known Activations