© 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. 171250
    Prev
    Next
    INDEX
    Explanations

    action verbs

    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
     advanced
    0.72
    advanced
    0.69
    Advanced
    0.67
     Advanced
    0.61
     f
    0.52
     avanzados
    0.48
     comm
    0.45
     wouldn
    0.45
     ف
    0.44
     limited
    0.42
    POSITIVE LOGITS
     assisted
    0.54
     suggested
    0.53
     followed
    0.52
     suivie
    0.52
     diikuti
    0.51
     seguida
    0.47
     identified
    0.46
     seguido
    0.46
    assisted
    0.45
     Assisted
    0.45
    Activations Density 0.002%

    No Known Activations