© 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. 20-GEMMASCOPE-TRANSCODER-16K
    7. 12137
    Prev
    Next
    INDEX
    Explanations

    words, phrases, and sentences related to a personal experience or hobby

    oai_token-act-pair · gemini-2.0-flash

    approximations

    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
     vecka
    -0.59
    numerusform
    -0.56
     veckan
    -0.56
    mtrl
    -0.55
     semaine
    -0.53
     semana
    -0.51
     informée
    -0.51
     Week
    -0.51
     veck
    -0.51
    thschild
    -0.50
    POSITIVE LOGITS
     nearly
    1.09
     almost
    0.95
     hundreds
    0.88
    nearly
    0.87
     dozens
    0.84
     approximately
    0.84
     Nearly
    0.83
    Nearly
    0.78
    almost
    0.73
     Almost
    0.71
    Activations Density 2.884%

    No Known Activations