© 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. 0-GEMMASCOPE-TRANSCODER-16K
    7. 3442
    Prev
    Next
    INDEX
    Explanations

    words related to legal terminology or to the history of people.

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    InvalidProtocol
    -0.93
    
    -0.87
    Bronnen
    -0.82
    TagMode
    -0.79
     WebApplication
    -0.78
    WebServlet
    -0.77
    MethodManager
    -0.76
     ExecuteAsync
    -0.73
     rospy
    -0.71
    urlpatterns
    -0.69
    POSITIVE LOGITS
    ohjel
    0.59
     aš
    0.59
     anticoag
    0.59
     tarko
    0.59
     Betten
    0.57
     munc
    0.54
     @"";
    0.54
    Superman
    0.53
     kanyang
    0.52
     laikā
    0.52
    Activations Density 9.853%

    No Known Activations