© 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. 7-GEMMASCOPE-TRANSCODER-16K
    7. 12456
    Prev
    Next
    INDEX
    Explanations

    words related to customer reviews and satisfaction.

    oai_token-act-pair · gemini-2.0-flash

    business reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.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
    apimachinery
    -0.47
    シル
    -0.45
    AutoresizingMask
    -0.42
     spindles
    -0.41
     globo
    -0.39
     width
    -0.39
    apad
    -0.39
    kedés
    -0.38
     HasFactory
    -0.38
    weisen
    -0.38
    POSITIVE LOGITS
    ViewImports
    0.90
     الحره
    0.89
    setVerticalGroup
    0.79
    adpleegd
    0.78
    Geplaatst
    0.71
     propOrder
    0.68
    Diwedd
    0.68
    RegressionTest
    0.68
    MLLoader
    0.66
     >=",
    0.63
    Activations Density 8.741%

    No Known Activations