© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 26440
    Prev
    Next
    INDEX
    Explanations

    philosophical question

    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
     of
    0.52
    zea
    0.52
    andel
    0.50
    istem
    0.49
     I
    0.48
     Zeus
    0.48
    ă
    0.48
    zi
    0.47
     sprzedaży
    0.47
    č
    0.47
    POSITIVE LOGITS
    ارا
    0.47
    ابق
    0.46
    رسٹ
    0.46
    الأ
    0.46
    Database
    0.45
    Código
    0.45
    الح
    0.44
    بر
    0.44
    الد
    0.44
    原有
    0.43
    Activations Density 0.000%

    No Known Activations