© 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. 2994
    Prev
    Next
    INDEX
    Explanations

    the pronoun "his" and the pronoun "he."

    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_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
    -3.58
    his
    -2.91
    彼の
    -2.48
     그의
    -2.38
     hänen
    -2.30
     seinem
    -2.25
    himself
    -2.23
     himself
    -2.23
     seiner
    -2.16
     njego
    -2.05
    POSITIVE LOGITS
     
    0.86
    .
    0.72
    ↵↵
    0.71
    The
    0.68
    <strong>
    0.68
    <em>
    0.68
    “
    0.67
    ↵
    0.65
    s
    0.64
    …
    0.64
    Activations Density 7.326%

    No Known Activations