© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 237318
    Prev
    Next
    INDEX
    Explanations

    Portland

    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_46_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
    ellipsis
    0.42
     Geophysical
    0.39
    newTask
    0.38
     devrez
    0.38
     taskId
    0.38
    .",[
    0.38
     uc
    0.36
     Jinping
    0.36
    津
    0.36
    FixedHeight
    0.36
    POSITIVE LOGITS
     Portland
    1.91
    Portland
    1.84
     portland
    1.70
    Oregon
    1.45
     Oregon
    1.44
     PORT
    1.09
     Пор
    1.06
    PORT
    1.02
    פור
    0.94
    POR
    0.92
    Activations Density 0.000%

    No Known Activations