© 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. 143647
    Prev
    Next
    INDEX
    Explanations

    mental

    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
     Desk
    0.41
    Desk
    0.39
    ρέπει
    0.39
     desk
    0.38
    ح
    0.38
     caps
    0.38
    OUT
    0.37
     часы
    0.37
    SOURCES
    0.37
     Knut
    0.37
    POSITIVE LOGITS
     condition
    0.47
    LocalStorage
    0.41
     condición
    0.41
     kondisi
    0.40
    条件
    0.39
     Conditions
    0.38
     conditions
    0.38
    condition
    0.38
    神経
    0.37
    }^{-}
    0.37
    Activations Density 0.002%

    No Known Activations