© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 4412
    Prev
    Next
    INDEX
    Explanations

    the word "zone" and words appearing in its immediate context

    oai_token-act-pair · gemini-2.0-flash

    zone

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    Parcelize
    -0.75
    makeText
    -0.68
     okuyayım
    -0.64
     courtier
    -0.64
    RegressionTest
    -0.61
     financials
    -0.61
     offseason
    -0.60
     Ress
    -0.60
    下载附件
    -0.60
     backstage
    -0.60
    POSITIVE LOGITS
     därför
    0.79
     pertanto
    0.77
     adicionais
    0.73
     entanto
    0.67
    Поэтому
    0.66
     поэтому
    0.65
     dlatego
    0.65
     étroite
    0.62
     tatuagens
    0.62
     therefore
    0.62
    Activations Density 1.607%

    No Known Activations