© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 124865
    Prev
    Next
    INDEX
    Explanations

    Khaled Mahmoud

    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_3_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
    rt
    0.90
    se
    0.78
    지
    0.77
    ，
    0.71
    v
    0.70
    ні
    0.68
    ।
    0.64
    ai
    0.63
    ll
    0.63
    reg
    0.63
    POSITIVE LOGITS
    ين
    0.82
    ותו
    0.68
     бонусу
    0.66
    绡
    0.66
     appBar
    0.64
     gecko
    0.64
    ים
    0.63
     champ
    0.63
     Aruba
    0.63
     ഉള്‍
    0.63
    Activations Density 0.006%

    No Known Activations