© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 74589
    Prev
    Next
    INDEX
    Explanations

    cinnamon sticks, oil and recipes

    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_31_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
    anyang
    0.38
    anya
    0.36
     social
    0.36
     domestic
    0.36
    encana
    0.36
    domestic
    0.36
     cosy
    0.36
     partition
    0.35
    <0xD3>
    0.34
    athed
    0.34
    POSITIVE LOGITS
     بتح
    0.42
     植物
    0.39
     inhomogeneities
    0.39
    溌
    0.38
    灘
    0.38
     በዚህ
    0.37
     Biod
    0.37
     ખાતે
    0.37
    翰
    0.37
    interpolate
    0.36
    Activations Density 0.001%

    No Known Activations