© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 18-GEMMASCOPE-TRANSCODER-16K
    7. 6373
    Prev
    Next
    INDEX
    Explanations

    words in a technical document about vehicle recalls

    oai_token-act-pair · gemini-2.0-flash

    machine repair issues

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_18/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.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
     transfieras
    -0.89
     تضيفلها
    -0.80
    KommentareTeilen
    -0.79
    lapsingToolbar
    -0.78
    IsContent
    -0.78
     EconPapers
    -0.78
     propOrder
    -0.77
    AndEndTag
    -0.75
     nahilalakip
    -0.74
    titleMargin
    -0.73
    POSITIVE LOGITS
     ver
    0.60
     Web
    0.49
     Ter
    0.48
     ter
    0.47
    ter
    0.46
     final
    0.44
    спек
    0.44
    ERIE
    0.44
     Western
    0.44
     Ver
    0.44
    Activations Density 1.370%

    No Known Activations