© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 460
    Prev
    Next
    INDEX
    Explanations

    laugh

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_44_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
    closure
    0.39
    radiated
    0.39
    КП
    0.39
    播放
    0.38
    转载
    0.37
    鱔
    0.37
    kében
    0.37
    ádza
    0.35
    etapkan
    0.35
    acat
    0.35
    POSITIVE LOGITS
     Cram
    0.44
     riot
    0.42
     riots
    0.42
     gas
    0.41
    方程式
    0.40
     Riot
    0.40
    nerv
    0.40
     출
    0.40
     গ্যাস
    0.40
     outwardly
    0.39
    Activations Density 0.009%

    No Known Activations