© 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. 4-GEMMASCOPE-TRANSCODER-16K
    7. 4265
    Prev
    Next
    INDEX
    Explanations

    words associated with love, faith, and devotion, especially those related to religion and marriage

    oai_token-act-pair · gemini-2.0-flash

    love

    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
     love
    -2.25
    Love
    -2.11
     Love
    -2.06
    love
    -2.02
     LOVE
    -1.89
    LOVE
    -1.80
     loves
    -1.52
    loves
    -1.20
     liefde
    -1.18
     Loves
    -1.16
    POSITIVE LOGITS
    ComponentModel
    0.60
     Kitch
    0.51
    okai
    0.48
     =>
    0.47
    ỏa
    0.45
    tuan
    0.45
     chaînes
    0.44
    ='#
    0.44
     Barnabas
    0.43
     baka
    0.43
    Activations Density 1.850%

    No Known Activations