© 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. 3-GEMMASCOPE-2-TRANSCODER-262K
    7. 40772
    Prev
    Next
    INDEX
    Explanations

    Aerion, Aerith

    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_3_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
     Aero
    0.69
    یر
    0.64
     위하여
    0.63
    },
    0.61
     သည်
    0.57
    場合には
    0.57
    irà
    0.57
     করিবার
    0.55
     위해
    0.55
    ätta
    0.55
    POSITIVE LOGITS
    م
    0.96
    ل
    0.93
    et
    0.91
    y
    0.87
    л
    0.87
    ت
    0.87
    \
    0.86
    د
    0.82
    м
    0.82
    т
    0.81
    Activations Density 0.003%

    No Known Activations