© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 0-GEMMASCOPE-2-TRANSCODER-262K
    7. 84863
    Prev
    Next
    INDEX
    Explanations

    RO or ро followed by a word

    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_0_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    2
    1.88
    ỡng
    1.51
     말미암아
    1.40
     인한
    1.38
    ।’
    1.34
    dır
    1.34
    9
    1.33
    kinase
    1.30
    もら
    1.27
    3
    1.27
    POSITIVE LOGITS
    ल
    1.88
     It
    1.70
    н
    1.65
    م
    1.63
    л
    1.55
    ল
    1.55
    大
    1.53
    ן
    1.53
    ل
    1.52
    is
    1.52
    Activations Density 0.000%

    No Known Activations