© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 4213
    Prev
    Next
    INDEX
    Explanations

    retirement, election, prison, grocery

    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_40_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
     lego
    0.22
    浆
    0.20
     collecting
    0.20
    structures
    0.20
    curvature
    0.19
     কমান্ডার
    0.19
    Collect
    0.19
    哄
    0.19
     begging
    0.19
    templates
    0.18
    POSITIVE LOGITS
    ளான
    0.21
     hovered
    0.20
    dsale
    0.20
     cálculo
    0.20
     تقری
    0.20
    ゐ
    0.19
     Apro
    0.19
     resort
    0.19
    诏
    0.19
    袭
    0.18
    Activations Density 0.037%

    No Known Activations