© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 203938
    Prev
    Next
    INDEX
    Explanations

    civil

    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
    Not in Any Lists

    No Comments

    Negative Logits
     civile
    0.52
     civil
    0.46
     CIVIL
    0.45
     граждан
    0.44
    civil
    0.44
     civiles
    0.43
    民
    0.42
     civilian
    0.41
    CIV
    0.40
    Civil
    0.39
    POSITIVE LOGITS
     محدود
    0.47
     الحد
    0.45
     ограничен
    0.42
     terbatas
    0.42
    ames
    0.41
     제한
    0.41
     limitado
    0.40
     limited
    0.39
    Ɩ
    0.39
     limitada
    0.38
    Activations Density 0.000%

    No Known Activations