© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 14418
    Prev
    Next
    INDEX
    Explanations

    Meta Platforms, Berkshire Hathaway

    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_40_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
     Capri
    0.40
     chino
    0.40
     করিয়াছে
    0.38
     UIButton
    0.37
     China
    0.37
    喁
    0.35
     中国
    0.35
     terminology
    0.34
     چینی
    0.34
     narrow
    0.34
    POSITIVE LOGITS
     clopen
    0.37
    番号
    0.37
     ওসি
    0.36
     depred
    0.36
    estamp
    0.35
    𝓀
    0.35
    yr
    0.35
    location
    0.35
    irono
    0.35
    intel
    0.33
    Activations Density 0.016%

    No Known Activations