© 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. 26-GEMMASCOPE-2-TRANSCODER-262K
    7. 195554
    Prev
    Next
    INDEX
    Explanations

    not isinstance

    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_26_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
     distractions
    0.38
     shortly
    0.38
    丂
    0.37
    ign
    0.37
    क्रामक
    0.36
     צי
    0.36
    坯
    0.36
     Bly
    0.36
     blem
    0.36
     fost
    0.36
    POSITIVE LOGITS
    ческих
    0.41
    сли
    0.41
     सेक
    0.39
    сності
    0.39
    Tunes
    0.38
    ത്തു
    0.38
    মাপ
    0.38
    дова
    0.37
    ново
    0.37
    穸
    0.37
    Activations Density 0.002%

    No Known Activations