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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 106800
    Prev
    Next
    INDEX
    Explanations

    Milk, Dark, Semi-sweet chocolate

    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_1_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
    ে
    1.17
    é
    1.16
    ان
    1.05
     dovrà
    1.05
    ين
    1.04
    ви
    1.02
    á
    1.02
    ه
    1.00
    ри
    1.00
    ução
    0.99
    POSITIVE LOGITS
    0.90
    2
    0.89
    d
    0.87
    nd
    0.85
     of
    0.84
    0
    0.84
          
    0.80
     installments
    0.78
    ्स
    0.77
     specialties
    0.77
    Activations Density 0.001%

    No Known Activations