© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 14408
    Prev
    Next
    INDEX
    Explanations

    words related to flavors, aromas, and food ingredients

    oai_token-act-pair · gemini-2.0-flash

    iris

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.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
    MigrationBuilder
    -0.68
    InstrumentedTest
    -0.64
    verwijspagina
    -0.64
     propOrder
    -0.62
     disambiguazione
    -0.61
    DebuggerNonUser
    -0.60
     Италијани
    -0.60
    sidemargin
    -0.59
    FTFY
    -0.59
     Italijanski
    -0.58
    POSITIVE LOGITS
     tropicales
    0.50
     يلي
    0.50
     brilh
    0.49
    참고
    0.49
     cot
    0.48
     députés
    0.44
    assertj
    0.43
     skai
    0.43
     agences
    0.42
     brilhante
    0.42
    Activations Density 3.135%

    No Known Activations