© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 8-GEMMASCOPE-TRANSCODER-16K
    7. 4919
    Prev
    Next
    INDEX
    Explanations

    phrases related to completion or what makes a good trip

    oai_token-act-pair · gemini-2.0-flash

    complete

    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
    Negative Logits
     Paglinawan
    -0.57
     unknownFields
    -0.56
    WebVitals
    -0.55
    зулта
    -0.54
     ReactDOM
    -0.53
    icylic
    -0.52
    oprene
    -0.52
     Sushi
    -0.52
     Tapatalk
    -0.51
     GeoNames
    -0.51
    POSITIVE LOGITS
    FunctionFlags
    0.53
     attracted
    0.53
     kasarigan
    0.50
     couver
    0.48
     rasanya
    0.46
    katy
    0.46
    aarrggbb
    0.45
    yorsunuz
    0.45
    ModelAttribute
    0.45
    ługo
    0.44
    Activations Density 0.743%

    No Known Activations