© 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. 6-GEMMASCOPE-TRANSCODER-16K
    7. 16312
    Prev
    Next
    INDEX
    Explanations

    words about people being together, relationships, company, and loneliness.

    oai_token-act-pair · gemini-2.0-flash

    company

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    esimo
    -0.54
    IsMutable
    -0.49
     herbes
    -0.49
    ábado
    -0.47
    ClientRect
    -0.46
     >=",
    -0.46
    DataSnapshot
    -0.46
     bosque
    -0.46
     konkurs
    -0.45
     investigating
    -0.45
    POSITIVE LOGITS
    verwijspagina
    0.79
     acompañado
    0.72
     companions
    0.72
    Companion
    0.70
    <bos>
    0.70
    Kaieteur
    0.69
     companion
    0.69
     companionship
    0.68
     Begle
    0.67
    begle
    0.66
    Activations Density 1.080%

    No Known Activations