© 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. 3-GEMMASCOPE-TRANSCODER-16K
    7. 6029
    Prev
    Next
    INDEX
    Explanations

    words or parts of words that are not common English

    oai_token-act-pair · gemini-2.0-flash

    med

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_3/width_16k/average_l0_54
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.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
     Med
    -0.99
     med
    -0.94
    med
    -0.93
    Med
    -0.87
    MED
    -0.82
     MED
    -0.74
     Interior
    -0.63
    medial
    -0.62
     uniform
    -0.60
     interior
    -0.60
    POSITIVE LOGITS
    AddTagHelper
    0.62
     kasarigan
    0.61
     pinulongan
    0.59
    RectangleBorder
    0.54
    ритори
    0.53
    WebControls
    0.50
     henvisninger
    0.50
     irmã
    0.49
    RegistryLite
    0.48
    DJANGO
    0.46
    Activations Density 11.456%

    No Known Activations