© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 11093
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to origins, familial relationships, and support systems

    oai_token-act-pair · gemini-2.0-flash

    Origins/locations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_20/width_16k/average_l0_11
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.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
     utafitiHapana
    -0.99
     myſelf
    -0.97
    StructEnd
    -0.92
     resourceCulture
    -0.90
    UnitTesting
    -0.90
    ьаж
    -0.89
    ंदीखरीदारी
    -0.88
     onCreateView
    -0.88
     raiſ
    -0.87
     MainAxisSize
    -0.86
    POSITIVE LOGITS
     piece
    0.53
     person
    0.53
     c
    0.49
     "
    0.48
     
    0.48
     institution
    0.48
    ض
    0.47
      
    0.47
     device
    0.47
     (
    0.47
    Activations Density 2.176%

    No Known Activations