© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 53067
    Prev
    Next
    INDEX
    Explanations

    environmental sustainability and impact

    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_31_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
     zn
    0.43
    ળા
    0.36
     serpent
    0.36
    ulpt
    0.35
     renter
    0.35
     $("#"
    0.35
    寜
    0.34
     hatch
    0.34
    ōng
    0.33
    斬
    0.33
    POSITIVE LOGITS
     eco
    0.74
     environmentally
    0.74
     экологи
    0.68
     sustainable
    0.63
     sustainability
    0.63
     carbon
    0.61
    环保
    0.60
     carbono
    0.59
     Eco
    0.57
     Sustainability
    0.57
    Activations Density 0.049%

    No Known Activations