© 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. 44-GEMMASCOPE-2-TRANSCODER-262K
    7. 253
    Prev
    Next
    INDEX
    Explanations

    local federal

    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_44_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
     Wise
    0.50
     wise
    0.44
     circular
    0.42
     Circular
    0.41
     Ki
    0.40
     WISE
    0.39
    ];//
    0.39
    වැ
    0.38
     வரி
    0.37
     Nac
    0.37
    POSITIVE LOGITS
     LOCAL
    0.53
    Local
    0.51
     Local
    0.50
    LOCAL
    0.47
     local
    0.46
    local
    0.45
     federal
    0.45
    federal
    0.42
    ederal
    0.41
     лока
    0.41
    Activations Density 0.024%

    No Known Activations