© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4315
    Prev
    Next
    INDEX
    Explanations

    mentions of "his" and other associated pronouns like he, him, or hers.

    oai_token-act-pair · gemini-2.0-flash

    his

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     her
    -1.29
     herself
    -0.98
     his
    -0.91
     hennes
    -0.88
    herself
    -0.82
     ihren
    -0.82
     ihrer
    -0.79
    她的
    -0.78
     ihrem
    -0.75
     ihre
    -0.73
    POSITIVE LOGITS
    __*/
    0.59
     Monfieur
    0.56
    complexContent
    0.54
     change
    0.52
    RegressionTest
    0.52
     transférez
    0.50
     alſo
    0.50
     điển
    0.49
    kloped
    0.48
    >())
    0.47
    Activations Density 2.624%

    No Known Activations