© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 21-GEMMASCOPE-TRANSCODER-16K
    7. 1704
    Prev
    Next
    INDEX
    Explanations

    references to the Department of Energy (DOE), its programs, and related scientific research

    oai_token-act-pair · gemini-2.0-flash

    references to "Office"

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.85
     يتيمه
    -0.80
     تضيفلها
    -0.75
    Personendaten
    -0.66
    posób
    -0.65
    spesies
    -0.63
    SequentialGroup
    -0.62
     gloire
    -0.61
     Audiodateien
    -0.60
     Wiktionnaire
    -0.60
    POSITIVE LOGITS
     Office
    0.54
    reactstrap
    0.46
    OS
    0.46
     Me
    0.46
    Билгалдахарш
    0.45
     arms
    0.45
    Office
    0.45
     office
    0.44
    板
    0.43
    iro
    0.42
    Activations Density 3.148%

    No Known Activations