© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 173190
    Prev
    Next
    INDEX
    Explanations

    publication contracts and deals

    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
     ਤ
    0.40
    aktif
    0.39
     கடல்
    0.38
     tril
    0.38
     기관
    0.38
    href
    0.37
     अकॉर्डिंग
    0.37
    ttä
    0.37
     −
    0.36
    ichlet
    0.36
    POSITIVE LOGITS
     Lets
    0.43
     MAKE
    0.41
     Make
    0.41
     make
    0.40
    学习
    0.39
     Bits
    0.39
     Makes
    0.38
     Lettuce
    0.38
     compensate
    0.38
    ното
    0.37
    Activations Density 0.000%

    No Known Activations