© 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. 8-GEMMASCOPE-TRANSCODER-16K
    7. 5100
    Prev
    Next
    INDEX
    Explanations

    people's names and associated words that appear in sports and academic biographies

    oai_token-act-pair · gemini-2.0-flash

    names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    oid
    -0.53
    way
    -0.51
    نسا
    -0.49
     Clements
    -0.48
    نس
    -0.48
     προσ
    -0.48
    ape
    -0.47
    oiden
    -0.46
    oide
    -0.46
    levant
    -0.46
    POSITIVE LOGITS
    InstrumentedTest
    0.77
    ViewImports
    0.71
     '\\;'
    0.69
    tvguidetime
    0.69
    Datuak
    0.66
     дописавши
    0.65
     Waray
    0.65
    Kanpo
    0.63
     betweenstory
    0.63
    Portale
    0.61
    Activations Density 5.257%

    No Known Activations