© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 12522
    Prev
    Next
    INDEX
    Explanations

    words that appear in lists and numbered rankings

    oai_token-act-pair · gemini-2.0-flash

    top

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     top
    -1.91
     Top
    -1.64
    Top
    -1.52
    top
    -1.52
     TOP
    -1.44
    TOP
    -1.43
     tops
    -1.33
    tops
    -1.17
    Tops
    -1.16
     टॉप
    -1.13
    POSITIVE LOGITS
    Shared
    0.50
    ("")){
    0.47
     vaga
    0.46
     cresc
    0.44
    heim
    0.44
    Mucho
    0.44
     Lode
    0.42
    has
    0.42
    Geograf
    0.42
    йн
    0.42
    Activations Density 30.454%

    No Known Activations