© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 10209
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to computer software downloads or map images

    oai_token-act-pair · gemini-2.0-flash

    Downloads of media/software

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Datuak
    -0.65
     NSCoder
    -0.58
     pleaſure
    -0.55
     cref
    -0.54
    commissioned
    -0.52
     chofe
    -0.49
    Kjelder
    -0.48
    ISupport
    -0.48
    Parcelize
    -0.48
    setVerticalGroup
    -0.47
    POSITIVE LOGITS
    Personensuche
    0.77
     Roskov
    0.65
     ویکی‌پدی
    0.65
     latest
    0.59
     تضيفلها
    0.58
     surety
    0.57
     HD
    0.56
    verwijspagina
    0.56
    tache
    0.54
     Hd
    0.54
    Activations Density 1.388%

    No Known Activations