© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 88821
    Prev
    Next
    INDEX
    Explanations

    fungal spores

    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_11_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
     Plants
    0.61
     D
    0.59
    m
    0.57
    N
    0.57
    t
    0.57
    ain
    0.56
     Greenhouse
    0.54
     पौधे
    0.54
     নীচে
    0.54
     Galleries
    0.53
    POSITIVE LOGITS
    倒入
    0.57
     generalize
    0.55
    愍
    0.53
     générateur
    0.53
     لاءِ
    0.52
    츈
    0.52
     আয়াত
    0.50
    投放
    0.50
    框架
    0.50
    Ꮡ
    0.49
    Activations Density 0.001%

    No Known Activations