© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 181159
    Prev
    Next
    INDEX
    Explanations

    latent

    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_24_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
    확
    0.46
    ॉर्डिंग
    0.43
    ड्रो
    0.43
     পোশাক
    0.41
    ையு
    0.41
    adığı
    0.40
     ఆరోగ
    0.40
    एप
    0.39
    theo
    0.39
     trabajó
    0.39
    POSITIVE LOGITS
     aff
    0.41
     J
    0.39
     petites
    0.38
     miz
    0.38
     RSS
    0.37
     gens
    0.37
     selfies
    0.37
     Lalu
    0.36
     Jin
    0.35
     Jud
    0.35
    Activations Density 0.014%

    No Known Activations