© 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. 13488
    Prev
    Next
    INDEX
    Explanations

    references to religion, especially related to church leadership and biblical references

    oai_token-act-pair · gemini-2.0-flash

    Christianity

    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
    Negative Logits
    fum
    -0.42
     Or
    -0.39
     alt
    -0.38
     His
    -0.37
     String
    -0.37
    ември
    -0.37
    ensiva
    -0.37
    myra
    -0.37
    ↵↵
    -0.37
    Ữ
    -0.35
    POSITIVE LOGITS
     تضيفلها
    1.09
    CloseOperation
    0.84
    CodedInputStream
    0.81
     bezeichneter
    0.80
    )++;
    0.79
    ########.
    0.78
     StatefulWidget
    0.75
    migrationBuilder
    0.73
    存于互联网档案馆
    0.73
     NSCoder
    0.72
    Activations Density 0.364%

    No Known Activations