© 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. 2-GEMMASCOPE-TRANSCODER-16K
    7. 9870
    Prev
    Next
    INDEX
    Explanations

    the word "encounter" sometimes as well as words related to music and mechanics

    oai_token-act-pair · gemini-2.0-flash

    encounter

    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
    Negative Logits
    <bos>
    -0.79
    ance
    -0.78
     encounter
    -0.72
     encounters
    -0.61
    ering
    -0.60
    fer
    -0.57
    Personensuche
    -0.57
     fer
    -0.54
    zen
    -0.53
     encountering
    -0.53
    POSITIVE LOGITS
    mappedBy
    0.78
     HasFactory
    0.71
     purpoſe
    0.70
    fromnode
    0.69
     /\.(
    0.66
     éta
    0.65
     venons
    0.63
    enumi
    0.62
     houſe
    0.60
     EconPapers
    0.59
    Activations Density 2.215%

    No Known Activations