© 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. 13303
    Prev
    Next
    INDEX
    Explanations

    instances of people talking to one another, with an emphasis on use of first and second person pronouns

    oai_token-act-pair · gemini-2.0-flash

    French

    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
     my
    -0.98
    my
    -0.88
     myself
    -0.86
     мое
    -0.76
     miei
    -0.72
     meines
    -0.71
    私の
    -0.69
     meinem
    -0.69
     me
    -0.68
     meiner
    -0.68
    POSITIVE LOGITS
    apimachinery
    0.71
     Efq
    0.70
     تضيفلها
    0.70
     houſe
    0.70
    IsMutable
    0.69
    Билгалдахарш
    0.65
    IsContent
    0.64
     المعيارى
    0.64
     Jefus
    0.64
     themſelves
    0.63
    Activations Density 7.563%

    No Known Activations