© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 11429
    Prev
    Next
    INDEX
    Explanations

    words related to probability, risk, and health

    oai_token-act-pair · gemini-2.0-flash

    Risk and images

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     Dostupné
    -0.55
     metálica
    -0.53
    PerPage
    -0.53
    ására
    -0.52
    RegistryLite
    -0.52
    cipais
    -0.49
    Населення
    -0.49
     vins
    -0.48
     насељу
    -0.47
    ::_('
    -0.47
    POSITIVE LOGITS
     AssemblyCulture
    1.00
    DeleteBehavior
    0.82
    Diweddarwch
    0.75
     beginnetje
    0.68
    ########.
    0.66
     HttpNotFound
    0.66
    iramente
    0.62
    NewUrlParser
    0.62
     INSPIRE
    0.59
    leneck
    0.58
    Activations Density 0.946%

    No Known Activations