© 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. 143645
    Prev
    Next
    INDEX
    Explanations

    perception

    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
     engaged
    0.44
     engage
    0.40
    PUBLIC
    0.40
     impegno
    0.40
    వడం
    0.40
     वित
    0.40
     engagement
    0.39
     citizenship
    0.39
     잘
    0.39
     ifade
    0.39
    POSITIVE LOGITS
    perception
    0.59
     perception
    0.54
     Perception
    0.50
     percib
    0.50
     perceived
    0.47
     perceiving
    0.46
     воспринима
    0.46
     percepción
    0.46
     perceptions
    0.45
     perce
    0.44
    Activations Density 0.005%

    No Known Activations