© 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. 180016
    Prev
    Next
    INDEX
    Explanations

    veget

    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
     جی
    0.45
    𝖚
    0.45
     nozzle
    0.41
    xym
    0.41
     علي
    0.40
     atores
    0.39
    ѳ
    0.39
    𝕦
    0.38
     anto
    0.38
    京
    0.38
    POSITIVE LOGITS
    ரும்
    0.44
    icity
    0.43
    }}}=\
    0.39
    CHER
    0.38
    VAE
    0.37
    ral
    0.37
     Archer
    0.36
    ractable
    0.36
    чери
    0.36
    InnerText
    0.36
    Activations Density 0.001%

    No Known Activations