© 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. 2-GEMMASCOPE-2-TRANSCODER-262K
    7. 109998
    Prev
    Next
    INDEX
    Explanations

    words following 's'

    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
     legalize
    1.02
    ות
    0.98
    is
    0.96
    ties
    0.92
     revolutionize
    0.89
    ിൽ
    0.89
    ጪ
    0.88
    떻
    0.87
    יי
    0.84
    ดังกล่าว
    0.84
    POSITIVE LOGITS
    า
    1.49
    ا
    1.17
     در
    1.09
     in
    1.05
    在
    1.04
     are
    1.02
    ва
    1.02
    ne
    1.02
     be
    1.01
    с
    0.98
    Activations Density 0.012%

    No Known Activations