© 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. 13288
    Prev
    Next
    INDEX
    Explanations

    the word "and" connected to other words.

    oai_token-act-pair · gemini-2.0-flash

    and

    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
    :✨
    -0.91
    LookAnd
    -0.82
     otomatig
    -0.82
     estekak
    -0.81
     nahilalakip
    -0.79
    ]--;
    -0.78
     дописавши
    -0.77
    WindowConstants
    -0.72
    تقاوى
    -0.71
    ագրություններ
    -0.71
    POSITIVE LOGITS
     presence
    0.56
     reputation
    0.53
     manner
    0.52
    presence
    0.52
     idea
    0.50
     notion
    0.50
     way
    0.47
    Migrations
    0.46
     belief
    0.43
     relationship
    0.42
    Activations Density 2.102%

    No Known Activations