© 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. 2961
    Prev
    Next
    INDEX
    Explanations

    lists of accomplishments by musical artists

    oai_token-act-pair · gemini-2.0-flash

    Broadcasts and recordings

    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
    AutoField
    -0.62
     genders
    -0.61
    期刊论文
    -0.57
    лаш
    -0.53
     noDo
    -0.49
     glau
    -0.49
    ungle
    -0.48
     furl
    -0.48
    Sucesor
    -0.48
     Acne
    -0.47
    POSITIVE LOGITS
    AndEndTag
    0.91
     betweenstory
    0.57
    Chham
    0.52
    rieu
    0.51
    verständlich
    0.51
     gehouden
    0.50
     MediaPlayer
    0.50
    orius
    0.50
    putstr
    0.48
    Placed
    0.48
    Activations Density 0.857%

    No Known Activations