© 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. 209075
    Prev
    Next
    INDEX
    Explanations

    per

    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
    graphics
    0.42
     প্রজাতন্ত্র
    0.39
    rägen
    0.39
     graphics
    0.39
    映
    0.38
     years
    0.38
    days
    0.37
    Days
    0.36
     impuestos
    0.36
     of
    0.36
    POSITIVE LOGITS
    你就
    0.45
     AND
    0.44
     बढ़ी
    0.42
    OBER
    0.41
     Prab
    0.41
     RBD
    0.41
     PLATE
    0.40
    ᱒
    0.40
     MAY
    0.39
     পছন্দ
    0.39
    Activations Density 0.001%

    No Known Activations