© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 154396
    Prev
    Next
    INDEX
    Explanations

    off or out

    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_50_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
    cast
    0.50
    ENDER
    0.46
    ender
    0.43
    rogation
    0.41
     DeS
    0.41
    چم
    0.40
    벨
    0.39
    ܡܪ
    0.38
     Laws
    0.38
     suitability
    0.38
    POSITIVE LOGITS
    ব্যাক
    0.39
    彧
    0.38
    ใส
    0.37
    यर्स
    0.36
    యర్
    0.36
     Face
    0.36
    ствуют
    0.36
     dispatched
    0.36
    यां
    0.36
     Allgemeine
    0.36
    Activations Density 0.008%

    No Known Activations