© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 1790
    Prev
    Next
    INDEX
    Explanations

    terms related to crafting, particularly paper crafting and card making, along with some color words.

    oai_token-act-pair · gemini-2.0-flash

    patterns or appearance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.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
    oredCriteria
    -0.78
    LabelTagHelper
    -0.77
     AssemblyCulture
    -0.73
     myſelf
    -0.73
    WireFormatLite
    -0.72
     itſelf
    -0.71
     fermés
    -0.70
     télécharge
    -0.69
    bbene
    -0.68
     AssemblyCompany
    -0.66
    POSITIVE LOGITS
     All
    0.49
     Al
    0.47
     micro
    0.47
     Pier
    0.45
     ta
    0.43
     Ber
    0.43
     Su
    0.42
     Sean
    0.42
     trans
    0.41
     default
    0.41
    Activations Density 2.189%

    No Known Activations