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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 19-GEMMASCOPE-TRANSCODER-16K
    7. 6778
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific experimental procedures

    oai_token-act-pair · gemini-2.0-flash

    ice

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.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
     EconPapers
    -0.66
    IUrlHelper
    -0.66
    出版年
    -0.59
    queryInterface
    -0.59
     Winaray
    -0.58
     springfox
    -0.58
    .*")]
    -0.56
    UnknownFieldSet
    -0.55
     saites
    -0.55
     AssemblyProduct
    -0.51
    POSITIVE LOGITS
     ice
    1.45
     Ice
    1.22
    Ice
    1.13
     hielo
    1.07
     ghiaccio
    1.02
    ice
    0.98
    氷
    0.82
     ICE
    0.78
     gelo
    0.77
    冰
    0.77
    Activations Density 1.005%

    No Known Activations