© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 7158
    Prev
    Next
    INDEX
    Explanations

    mentions of authors, books or writing

    oai_token-act-pair · gemini-2.0-flash

    authors and writers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     незавершена
    -0.82
    Билгалдахарш
    -0.76
    EndProject
    -0.67
    zyż
    -0.67
     crossorigin
    -0.63
    PerformLayout
    -0.60
    下载附件
    -0.60
    RenderAtEndOf
    -0.59
    Portale
    -0.57
    rö
    -0.57
    POSITIVE LOGITS
     authors
    1.54
     author
    1.45
     writers
    1.38
     writer
    1.31
    authors
    1.29
     Authors
    1.28
     Autoren
    1.22
     Author
    1.20
     Writer
    1.14
    Author
    1.13
    Activations Density 4.346%

    No Known Activations