© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 254040
    Prev
    Next
    INDEX
    Explanations

    pad or mad

    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_56_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
     M
    1.13
     mom
    0.88
    母亲
    0.82
    M
    0.82
    母親
    0.82
    父亲
    0.82
    父親
    0.81
     М
    0.81
    М
    0.81
     الم
    0.80
    POSITIVE LOGITS
     pad
    1.55
    pad
    1.42
    Pad
    1.41
     Pad
    1.40
     mad
    1.32
    Mad
    1.30
     Mad
    1.27
    mad
    1.22
     pads
    1.07
     PAD
    1.05
    Activations Density 0.012%

    No Known Activations