© 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. 30798
    Prev
    Next
    INDEX
    Explanations

    Lakshmana

    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
    Negative Logits
     negeri
    1.00
     Negeri
    0.76
    Neg
    0.61
     neg
    0.61
     Neg
    0.59
    ネ
    0.57
     né
    0.53
     নে
    0.50
     네
    0.50
     Nee
    0.50
    POSITIVE LOGITS
    san
    0.52
    San
    0.46
    SAN
    0.46
    क्षण
    0.44
    ks
    0.44
    sanitize
    0.44
    aksana
    0.44
    aks
    0.43
    кса
    0.43
    ксана
    0.43
    Activations Density 0.003%

    No Known Activations