© 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. 9307
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to physical configuration or adjustment

    oai_token-act-pair · gemini-2.0-flash

    adjust

    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
    adjust
    -0.87
    Adjust
    -0.85
     adjust
    -0.82
     adjusting
    -0.82
     adjusted
    -0.78
     adjusts
    -0.74
     Adjust
    -0.73
     adjustments
    -0.72
     adjustment
    -0.71
     Adjusting
    -0.70
    POSITIVE LOGITS
    uxxxx
    0.75
     незавершена
    0.75
    yntaxException
    0.72
    ItemBackground
    0.71
    NUMX
    0.71
     utafitiHapana
    0.69
    ToAction
    0.68
     Efq
    0.67
     moschino
    0.66
    ')")
    0.66
    Activations Density 16.436%

    No Known Activations