© 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. 13051
    Prev
    Next
    INDEX
    Explanations

    references, quotes, and speakers, especially doctors

    oai_token-act-pair · gemini-2.0-flash

    fragments of quotes or references

    np_token-act-pair-logits · gpt-4o-mini

    Names and titles

    np_max-act-logits · gemini-2.0-flash
    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
    SharedCtor
    -0.63
    @[+][
    -0.56
    EDEFAULT
    -0.53
    PointerException
    -0.50
    Viitteet
    -0.49
     ProductService
    -0.49
     [''],
    -0.48
    grine
    -0.47
     nature
    -0.47
    EPS
    -0.47
    POSITIVE LOGITS
    ériale
    0.51
     onCreateView
    0.47
    VersionUID
    0.47
     onOptions
    0.47
    بوابة
    0.47
    hidupan
    0.46
     signed
    0.46
     côtes
    0.46
     QName
    0.46
     commerciales
    0.45
    Activations Density 0.587%

    No Known Activations