© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 14113
    Prev
    Next
    INDEX
    Explanations

    possessive personal pronouns, especially "her"

    oai_token-act-pair · gemini-2.0-flash

    her

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     his
    -0.68
     sur
    -0.60
     qu
    -0.60
    __(/*!
    -0.59
     del
    -0.59
     kes
    -0.58
     les
    -0.57
     co
    -0.56
     himself
    -0.56
    huma
    -0.55
    POSITIVE LOGITS
    <bos>
    2.94
     itſelf
    0.98
     Monfieur
    0.91
     Shakspeare
    0.82
     raiſ
    0.81
     pleaſure
    0.75
    ſelves
    0.73
     faſt
    0.71
     myſelf
    0.70
     Jefus
    0.69
    Activations Density 0.678%

    No Known Activations