© 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. 9360
    Prev
    Next
    INDEX
    Explanations

    invitations to events and opportunities to express opinions

    oai_token-act-pair · gemini-2.0-flash

    invite

    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
    Negative Logits
     invite
    -1.90
     invitation
    -1.85
     invites
    -1.74
     invited
    -1.71
     Invite
    -1.70
     inviting
    -1.63
    Invite
    -1.60
     invitations
    -1.59
    invite
    -1.57
    invited
    -1.45
    POSITIVE LOGITS
    ViewFeatures
    0.78
    posedge
    0.73
     continúas
    0.63
     nahilalakip
    0.59
    AddHtmlAttribute
    0.56
    stdbool
    0.56
    awtextra
    0.56
    InjectAttribute
    0.56
    /*++
    0.55
    UpInside
    0.54
    Activations Density 16.058%

    No Known Activations