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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-2B
    5. 2-GEMMASCOPE-TRANSCODER-16K
    7. 10502
    Prev
    Next
    INDEX
    Explanations

    the word "one" in the middle of scientific text

    oai_token-act-pair · gemini-2.0-flash

    One

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_2/width_16k/average_l0_49
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.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
     One
    -1.70
    One
    -1.40
     ONE
    -1.00
    ONE
    -0.94
     Another
    -0.79
     Ein
    -0.70
     Ones
    -0.67
     Two
    -0.63
     In
    -0.60
    Another
    -0.59
    POSITIVE LOGITS
     HasFactory
    0.93
     démocr
    0.91
    TagMode
    0.90
     chré
    0.88
     automatiques
    0.85
     initComponents
    0.82
     esternos
    0.82
     myſelf
    0.81
     quelcon
    0.81
    retudo
    0.81
    Activations Density 0.441%

    No Known Activations