© 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. 9507
    Prev
    Next
    INDEX
    Explanations

    words associated with pregnancy, birth, and abortion

    oai_token-act-pair · gemini-2.0-flash

    life

    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
    ExtendWith
    -0.49
     lou
    -0.48
     Oss
    -0.46
     nhu
    -0.45
    zoic
    -0.44
     aureus
    -0.44
     inoxidable
    -0.43
    jimo
    -0.43
     record
    -0.43
    setUserId
    -0.43
    POSITIVE LOGITS
    findpost
    0.93
    GEBURTSDATUM
    0.90
    MigrationBuilder
    0.83
     pregnancy
    0.78
     незавершена
    0.78
     Pregnancy
    0.74
    WebElementEntity
    0.69
    Демографія
    0.68
    StoryboardSegue
    0.66
    Pregnancy
    0.66
    Activations Density 0.591%

    No Known Activations