© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4433
    Prev
    Next
    INDEX
    Explanations

    javascript code snippets

    oai_token-act-pair · gemini-2.0-flash

    load

    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
     vastaan
    -0.49
    BooleanField
    -0.48
     AppComponent
    -0.47
    onViewCreated
    -0.47
     témoignage
    -0.45
    vás
    -0.44
     siitä
    -0.44
    BINARY
    -0.43
     ComVisible
    -0.43
    ukunfts
    -0.41
    POSITIVE LOGITS
    webElementXpaths
    0.65
    脚注の使い方
    0.64
     oprot
    0.61
     Normdatei
    0.60
     pann
    0.58
    Portale
    0.58
    tvguidetime
    0.58
    WebVitals
    0.57
    Datuak
    0.57
    Географи
    0.57
    Activations Density 0.936%

    No Known Activations