© 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. 36830
    Prev
    Next
    INDEX
    Explanations

    manifest_version: 3

    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
     пло
    0.40
    接近
    0.39
    চ্
    0.38
     దృష్టి
    0.38
    ционно
    0.36
    जनिक
    0.35
     안정
    0.35
    雳
    0.35
    गराज
    0.34
     മതി
    0.34
    POSITIVE LOGITS
     sour
    0.37
     vampire
    0.37
     Radi
    0.34
     irrigation
    0.34
     authenticity
    0.34
    Zi
    0.33
     phy
    0.33
    ட்ர
    0.33
    arad
    0.33
     decay
    0.33
    Activations Density 0.005%

    No Known Activations