© 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. 12-GEMMASCOPE-TRANSCODER-16K
    7. 8225
    Prev
    Next
    INDEX
    Explanations

    references to publications and code

    oai_token-act-pair · gemini-2.0-flash

    Academic/scientific papers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_12/width_16k/average_l0_6
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ̓
    -0.61
    PerformLayout
    -0.59
    amerikanischer
    -0.57
     MainAxisSize
    -0.57
    gbaar
    -0.57
    χρι
    -0.55
    vician
    -0.53
    felves
    -0.52
    MergeFrom
    -0.51
     InputDecoration
    -0.51
    POSITIVE LOGITS
     lccn
    0.54
    <bos>
    0.51
     ***!
    0.48
    igshid
    0.46
     nakalista
    0.46
    eni
    0.43
    st
    0.43
    TestFixture
    0.43
    нін
    0.41
    ft
    0.41
    Activations Density 9.747%

    No Known Activations