© 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. 14593
    Prev
    Next
    INDEX
    Explanations

    descriptive language in scientific experiments and cooking recipes

    oai_token-act-pair · gemini-2.0-flash

    recipes and scientific methods

    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
    ilà
    -0.55
    lez
    -0.54
    RegressionTest
    -0.49
    ungsver
    -0.47
    wor
    -0.47
     الحره
    -0.47
    /}{
    -0.47
    ഴ
    -0.47
     CJ
    -0.47
    ới
    -0.46
    POSITIVE LOGITS
    setVerticalGroup
    0.74
    RTGC
    0.72
    SBATCH
    0.65
     ModelExpression
    0.65
     defaultstate
    0.63
    ImageContext
    0.63
     unknownFields
    0.62
     FetchType
    0.62
     nzuri
    0.61
     Viceroy
    0.60
    Activations Density 4.162%

    No Known Activations