© 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. 4-GEMMASCOPE-TRANSCODER-16K
    4. 13113
    Prev
    Next
    INDEX
    Explanations

    the word "pan" and words that often go with it in several different contexts

    oai_token-act-pair · gemini-2.0-flash

    pan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.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
     pan
    -2.41
    Pan
    -2.23
     Pan
    -2.22
    pan
    -2.09
     PAN
    -1.63
    PAN
    -1.60
     pans
    -1.56
    pans
    -1.33
     Pans
    -1.27
     пан
    -1.13
    POSITIVE LOGITS
    UrlResolution
    0.94
    tonsoft
    0.77
    principalTable
    0.75
    amaño
    0.74
    TagMode
    0.72
    bonucleic
    0.70
    DoubleQuotes
    0.68
     виправивши
    0.67
     conseguenza
    0.67
    }],
    
    0.66
    Activations Density 2.832%

    No Known Activations