© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16299
    Prev
    Next
    INDEX
    Explanations

    mentions of people referred to by pronouns

    oai_token-act-pair · gemini-2.0-flash

    they

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    they
    -1.02
     they
    -1.01
    THEY
    -0.85
    They
    -0.81
     They
    -0.77
     THEY
    -0.74
     архивлан
    -0.69
    enumi
    -0.69
    GEBURTS
    -0.67
     deles
    -0.66
    POSITIVE LOGITS
    <bos>
    0.78
     considérons
    0.60
     estekak
    0.54
    reszcie
    0.50
    لينكات
    0.50
    rawdę
    0.49
     fallu
    0.49
     referenties
    0.48
    ‍♂️
    0.48
    raszam
    0.47
    Activations Density 6.002%

    No Known Activations