© 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. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106805
    Prev
    Next
    INDEX
    Explanations

    Ensuring correctness and quality

    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_1_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
    ו
    1.16
    c
    1.05
    ک
    1.04
    ב
    1.02
    ت
    1.00
    ب
    1.00
    ל
    0.98
    il
    0.94
    d
    0.93
    م
    0.92
    POSITIVE LOGITS
    ного
    0.92
    し
    0.87
    ﺣ
    0.87
    ер
    0.84
    ﻋ
    0.84
    ﺪ
    0.84
     يع
    0.84
     ಆದರೆ
    0.83
    ﺮ
    0.83
     فی
    0.82
    Activations Density 0.004%

    No Known Activations