© 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. 22-GEMMASCOPE-TRANSCODER-16K
    7. 10029
    Prev
    Next
    INDEX
    Explanations

    measurement terms in recipes

    oai_token-act-pair · gemini-2.0-flash

    food recipes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
    invokeLater
    -0.49
    diğinde
    -0.48
     discriminant
    -0.48
    ilius
    -0.46
     Huss
    -0.46
     reces
    -0.46
    ennis
    -0.46
     anhydride
    -0.45
    ArrayOf
    -0.44
     kyt
    -0.44
    POSITIVE LOGITS
     BoxDecoration
    0.69
     resourceCulture
    0.65
    makeText
    0.63
    Think
    0.63
     Think
    0.61
    EndContext
    0.58
    WriteTagHelper
    0.58
     think
    0.58
    VersionUID
    0.58
    endpush
    0.58
    Activations Density 0.986%

    No Known Activations