© 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. 57-GEMMASCOPE-2-TRANSCODER-262K
    7. 228457
    Prev
    Next
    INDEX
    Explanations

    multiple languages

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_57_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
     curbing
    0.40
     Rin
    0.39
    ӓ
    0.38
    䛺
    0.38
     rims
    0.38
     JOSEPH
    0.38
    嗣
    0.37
     rim
    0.36
     Heels
    0.36
     dimiliki
    0.36
    POSITIVE LOGITS
    re
    0.38
    anto
    0.36
     동
    0.36
     आंसू
    0.36
     দুর্ভিক্ষের
    0.36
    云计算
    0.35
    iciency
    0.35
    athlon
    0.35
    lation
    0.33
    sever
    0.33
    Activations Density 0.000%

    No Known Activations