© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 20-GEMMASCOPE-TRANSCODER-16K
    7. 13519
    Prev
    Next
    INDEX
    Explanations

    the articles "a," "an," and "the" when they appear before descriptive words or phrases related to amounts or specifications.

    oai_token-act-pair · gemini-2.0-flash

    a

    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
     виправивши
    -0.86
     asiatique
    -0.74
     direta
    -0.71
     theſe
    -0.68
     térmico
    -0.67
     schuldig
    -0.67
     alguien
    -0.66
     térmica
    -0.65
     zelve
    -0.65
     alguém
    -0.65
    POSITIVE LOGITS
     region
    0.48
     multi
    0.47
    دانشنامهٔ
    0.47
     opérateur
    0.46
    UnknownFieldSet
    0.46
    contentLoaded
    0.45
     such
    0.44
    inam
    0.44
     burn
    0.43
    ://
    0.42
    Activations Density 2.795%

    No Known Activations