© 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. 12285
    Prev
    Next
    INDEX
    Explanations

    words that begin a sentence and numbers, sometimes together

    oai_token-act-pair · 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
     Decide
    -1.28
     decides
    -1.25
     deciding
    -1.25
     decide
    -1.24
    decide
    -1.23
    determine
    -1.13
     Normdatei
    -1.13
     determines
    -1.12
    determin
    -1.11
    Decide
    -1.11
    POSITIVE LOGITS
    gar
    0.66
     Gar
    0.63
     N
    0.58
    GAR
    0.56
     single
    0.56
     attached
    0.56
     triple
    0.54
     
    0.54
     GAR
    0.52
    attached
    0.50
    Activations Density 0.340%

    No Known Activations