Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 20-GEMMASCOPE-TRANSCODER-16K
    4. 16218
    Prev
    Next
    INDEX
    Explanations

    words and phrases such as "originally", "initially", "now, and "while" indicating the passing of time or sequential actions.

    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
     which
    -0.73
     who
    -0.70
    who
    -0.63
    which
    -0.61
     that
    -0.54
     and
    -0.53
    ılı
    -0.49
     que
    -0.48
     yang
    -0.47
     WHICH
    -0.46
    POSITIVE LOGITS
     nahilalakip
    1.27
     समीक्षाओं
    1.04
    EndContext
    0.98
    SharedDtor
    0.88
     lenker
    0.83
    WithIOException
    0.82
    évaluateur
    0.78
    تقاوى
    0.77
    Personendaten
    0.77
     الرياضيه
    0.72
    Activations Density 4.677%

    No Known Activations