© 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. 208889
    Prev
    Next
    INDEX
    Explanations

    surveillance

    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
     watchful
    1.04
     surveillance
    0.99
     vigil
    0.99
     vigilant
    0.92
     vigilancia
    0.91
     б
    0.90
     cz
    0.89
     vigilance
    0.88
    เ
    0.88
     Vigil
    0.85
    POSITIVE LOGITS
    Sur
    2.33
    sur
    2.28
     Sur
    2.19
     sur
    1.98
     SUR
    1.83
    SUR
    1.66
     sür
    1.53
     surv
    1.27
     Surat
    1.26
     سور
    1.25
    Activations Density 0.003%

    No Known Activations