© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 155742
    Prev
    Next
    INDEX
    Explanations

    Energy

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_60_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
     isothermal
    0.48
     isother
    0.43
     decorations
    0.37
     isle
    0.37
    CONDUCT
    0.36
    を持ち
    0.35
    𝗶
    0.34
    拿起
    0.34
     conduct
    0.34
     retos
    0.34
    POSITIVE LOGITS
     Energy
    0.59
     énergie
    0.59
    Energy
    0.57
    energy
    0.56
     energy
    0.53
    エネルギー
    0.52
     에너지
    0.52
    énergie
    0.49
     энергия
    0.47
     енер
    0.46
    Activations Density 0.021%

    No Known Activations