© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 159514
    Prev
    Next
    INDEX
    Explanations

    jpeg artifacts

    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
    ב
    1.20
    는
    1.15
    り
    1.04
    هم
    1.03
    ני
    1.01
    rying
    0.99
    ग
    0.99
    오
    0.98
     it
    0.97
    of
    0.96
    POSITIVE LOGITS
    ер
    1.40
    ам
    1.12
    态度
    1.06
    تش
    1.05
    تان
    1.03
    تها
    1.02
    تين
    1.02
    ел
    1.02
    انی
    1.01
    تي
    0.98
    Activations Density 0.001%

    No Known Activations