© 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-3-27B-IT
    5. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 179915
    Prev
    Next
    INDEX
    Explanations

    Judge conditional inputs

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     scarcity
    0.46
    EMY
    0.43
     Katy
    0.40
    カタ
    0.39
    kitty
    0.39
     UITableView
    0.38
    マット
    0.38
     Kathleen
    0.38
     Kathy
    0.38
    卖
    0.38
    POSITIVE LOGITS
    рян
    0.43
     دیں
    0.41
    gsm
    0.40
    igera
    0.40
    upart
    0.39
    वाना
    0.39
    BW
    0.38
    gore
    0.38
    дали
    0.37
    Iceland
    0.37
    Activations Density 0.009%

    No Known Activations