© 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. 15-GEMMASCOPE-2-TRANSCODER-262K
    7. 19593
    Prev
    Next
    INDEX
    Explanations

    clean energy and technology

    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_15_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
    乆
    0.55
     toxicants
    0.52
    级别
    0.51
    नीर
    0.51
    𒃲
    0.50
    `);
    0.50
    ASCADE
    0.50
     pptn
    0.49
    念念
    0.49
    闔
    0.49
    POSITIVE LOGITS
     Technology
    0.59
    ta
    0.53
    íses
    0.52
    mina
    0.52
     technology
    0.51
     Industries
    0.51
     are
    0.51
    Technology
    0.50
     Discipl
    0.49
     Industry
    0.49
    Activations Density 0.008%

    No Known Activations