© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 10562
    Prev
    Next
    INDEX
    Explanations

    words related to transporting computer hardware and packaging safely

    oai_token-act-pair · gemini-2.0-flash

    technical terms or keywords

    np_token-act-pair-logits · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    Sucesor
    -0.58
    ^(@)
    -0.56
     misunderstood
    -0.56
    rrggbb
    -0.55
    Rujuakan
    -0.54
    SaveChangesAsync
    -0.54
    ADVERTISEMENT
    -0.52
    IndentedString
    -0.52
     bershka
    -0.52
     heridos
    -0.51
    POSITIVE LOGITS
    AutoField
    0.59
     case
    0.56
    ophanes
    0.51
    comuna
    0.47
    otry
    0.47
    tagHelper
    0.47
     demografica
    0.47
     cases
    0.46
    ikations
    0.45
    ьаж
    0.45
    Activations Density 1.436%

    No Known Activations