© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 24977
    Prev
    Next
    INDEX
    Explanations

    pilot

    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_10_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
    ר
    1.09
     is
    1.02
    a
    0.96
    ה
    0.94
    ות
    0.89
    !
    0.83
    บ
    0.80
    บน
    0.79
    اح
    0.77
    o
    0.75
    POSITIVE LOGITS
    áme
    0.88
     piloted
    0.87
    အတွ
    0.84
     पायलट
    0.80
     первых
    0.79
     পাইল
    0.77
     সর্বপ্রথম
    0.76
    ā
    0.76
     Pilot
    0.75
    фин
    0.75
    Activations Density 0.013%

    No Known Activations