© 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. 6239
    Prev
    Next
    INDEX
    Explanations

    words that could be used to rank or compare things numerically

    oai_token-act-pair · gemini-2.0-flash

    best or worst in category

    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
     vœux
    -0.99
     épaules
    -0.96
     âmes
    -0.94
     bienfaits
    -0.92
     bénéfices
    -0.90
     prochaines
    -0.88
     pouvoirs
    -0.88
     dieux
    -0.84
     églises
    -0.81
     genoux
    -0.78
    POSITIVE LOGITS
     disambiguazione
    0.81
     تضيفلها
    0.75
     calculators
    0.75
     beacons
    0.75
     calendars
    0.75
     installations
    0.74
    (!__
    0.73
    tagHelperRunner
    0.72
     booths
    0.72
     machines
    0.71
    Activations Density 3.263%

    No Known Activations