© 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. 21-GEMMASCOPE-TRANSCODER-16K
    7. 11743
    Prev
    Next
    INDEX
    Explanations

    commas within sentences and phrases about business, economics, geography, or medicine

    oai_token-act-pair · gemini-2.0-flash

    words related to statements or clauses

    np_token-act-pair-logits · gpt-4o-mini

    commas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.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
    ,
    -0.50
    kannya
    -0.42
    چنین
    -0.38
    archiviato
    -0.37
    bueno
    -0.36
    ாள
    -0.36
    buie
    -0.34
    ρός
    -0.33
     Likewise
    -0.33
    ąc
    -0.32
    POSITIVE LOGITS
     which
    2.56
    which
    2.05
     WHICH
    1.87
     Which
    1.70
     whose
    1.70
    Which
    1.67
     who
    1.54
    whose
    1.52
     które
    1.52
     cuya
    1.48
    Activations Density 2.636%

    No Known Activations