© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173946
    Prev
    Next
    INDEX
    Explanations

    gear

    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_20_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
    ექ
    0.50
    레
    0.42
    배
    0.42
    크
    0.41
    सोशल
    0.40
    ุ่ม
    0.40
    색
    0.39
    小学生
    0.39
    포
    0.38
    ẹ
    0.38
    POSITIVE LOGITS
     मेला
    0.49
     EVER
    0.46
     confir
    0.45
     निभा
    0.45
     tent
    0.44
     καθ
    0.43
     продукти
    0.42
     प्रस्तुत
    0.42
     mientras
    0.42
     medan
    0.41
    Activations Density 0.002%

    No Known Activations