© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-TRANSCODER-262K
    4. 30296
    Prev
    Next
    INDEX
    Explanations

    participate, participation, actively

    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
    िसिटी
    0.40
     ayud
    0.36
     सां
    0.35
     writ
    0.34
    =\{\
    0.34
     Saito
    0.34
     bank
    0.33
     SSA
    0.33
    \}=
    0.33
     सहायता
    0.33
    POSITIVE LOGITS
     active
    2.14
     актив
    2.00
     actively
    1.95
    active
    1.93
     Active
    1.90
    Active
    1.88
     aktif
    1.88
     активно
    1.83
     सक्रिय
    1.75
     ACTIVE
    1.73
    Activations Density 0.061%

    No Known Activations