© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 13595
    Prev
    Next
    INDEX
    Explanations

    mentions of groups being referred to by 'those', typically followed by a relative pronoun and subsequent criteria

    oai_token-act-pair · gemini-2.0-flash

    those

    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
    Negative Logits
     Those
    -0.80
    Those
    -0.78
     those
    -0.77
    those
    -0.74
     ceux
    -0.57
     THOSE
    -0.54
    那些
    -0.54
     aqueles
    -0.52
     aquellos
    -0.52
     coloro
    -0.49
    POSITIVE LOGITS
     Baillargeon
    0.82
     estekak
    0.81
    SharedCtor
    0.77
     BoxFit
    0.74
    DockStyle
    0.74
    
    0.73
     createState
    0.71
    tonsoft
    0.71
     BoxDecoration
    0.69
    脚注の使い方
    0.69
    Activations Density 13.733%

    No Known Activations