© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 59711
    Prev
    Next
    INDEX
    Explanations

    raining

    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
    1
    1.30
    م
    1.30
    the
    1.22
    ag
    1.19
    res
    1.18
    ان
    1.18
    ح
    1.17
    ay
    1.16
    that
    1.12
    مت
    1.12
    POSITIVE LOGITS
    al
    1.20
    이랑
    0.96
    이지만
    0.94
    "。
    0.93
    িত্ত
    0.92
     zwią
    0.90
     배웠
    0.89
     stanie
    0.87
     shove
    0.86
    ы
    0.85
    Activations Density 0.001%

    No Known Activations