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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-2B
    3. 22-GEMMASCOPE-TRANSCODER-16K
    4. 10461
    Prev
    Next
    INDEX
    Explanations

    common English words, especially "the", in sports reporting

    oai_token-act-pair · gemini-2.0-flash

    the

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_22/width_16k/average_l0_15
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.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
     in
    -0.47
     
    -0.45
     bek
    -0.42
     kost
    -0.39
    et
    -0.38
    B
    -0.37
    -
    -0.37
    лев
    -0.37
     Fischer
    -0.36
    leg
    -0.36
    POSITIVE LOGITS
    protoimpl
    1.05
     Lightboxes
    1.02
     виправивши
    0.95
     Мексичка
    0.91
    出版年
    0.91
     consultato
    0.88
    ///</
    0.87
     ReactDOM
    0.85
     سكانية
    0.85
    IUrlHelper
    0.84
    Activations Density 0.266%

    No Known Activations