© 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. 13260
    Prev
    Next
    INDEX
    Explanations

    pronouns used as subjects of a sentence paired with action verbs describing people performing activities.

    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_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
    Not in Any Lists

    No Comments

    Negative Logits
     theirs
    -0.90
     their
    -0.85
    Their
    -0.83
    They
    -0.83
    their
    -0.82
     they
    -0.82
    they
    -0.79
     themſelves
    -0.73
     themselves
    -0.72
     thier
    -0.72
    POSITIVE LOGITS
    \{\\
    0.54
    บาท
    0.51
    liothèque
    0.50
     समीक्षाओं
    0.48
     Réponses
    0.48
    ̍
    0.48
     Da
    0.47
    Bronnen
    0.47
    ,:);
    0.47
    EndInit
    0.46
    Activations Density 13.361%

    No Known Activations