© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 217383
    Prev
    Next
    INDEX
    Explanations

    Video games

    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_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     V
    0.47
     வ
    0.44
    vb
    0.40
     В
    0.40
     Rb
    0.40
     Mecca
    0.39
     v
    0.39
     Smack
    0.39
    YB
    0.39
     W
    0.38
    POSITIVE LOGITS
     जिंद
    0.41
     अंश
    0.40
     тап
    0.40
     ຊ
    0.39
     mũi
    0.39
    ческим
    0.38
     cof
    0.38
    ным
    0.38
    mong
    0.38
    anganan
    0.38
    Activations Density 0.000%

    No Known Activations