© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 0-GEMMASCOPE-TRANSCODER-16K
    7. 9413
    Prev
    Next
    INDEX
    Explanations

    the word "body" and other words related to it, or words directly connected to the word "body".

    oai_token-act-pair · gemini-2.0-flash

    body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_0/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.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
    <bos>
    -1.18
    '
    -0.91
    ’
    -0.86
    ‘
    -0.82
    ↵↵
    -0.80
    ↵
    -0.73
     
    -0.69
    <strong>
    -0.68
    s
    -0.59
    *
    -0.57
    POSITIVE LOGITS
     pinulongan
    0.95
     idéia
    0.93
    DebuggerNonUser
    0.92
     cherchés
    0.91
     greateſt
    0.91
    saraba
    0.91
     EconPapers
    0.90
    AddTagHelper
    0.89
     ویکی‌پدیا
    0.87
     mijne
    0.87
    Activations Density 0.835%

    No Known Activations