© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 107750
    Prev
    Next
    INDEX
    Explanations

    sits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_2_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
    ج
    2.02
    ف
    1.96
    ק
    1.87
    ط
    1.77
    ك
    1.71
    م
    1.59
    ד
    1.58
    ח
    1.56
    ق
    1.54
    人
    1.52
    POSITIVE LOGITS
     terminus
    0.90
     mentored
    0.90
     chaired
    0.89
     données
    0.88
     stenosis
    0.88
     skyrocketed
    0.86
     propelled
    0.85
     пищи
    0.84
    2
    0.84
     sat
    0.84
    Activations Density 0.000%

    No Known Activations