© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 83307
    Prev
    Next
    INDEX
    Explanations

    pert

    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_53_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
    ruiter
    0.48
    ளைஞ
    0.42
    נען
    0.40
    merich
    0.40
    囗
    0.39
     Menn
    0.39
    ラッピング
    0.38
     honey
    0.38
    Honey
    0.38
     NN
    0.38
    POSITIVE LOGITS
     pert
    1.07
    Pert
    0.88
     Pert
    0.86
    pert
    0.73
     perturbation
    0.63
    PERT
    0.59
     퍼
    0.59
    perturb
    0.57
     pers
    0.55
     perturbative
    0.55
    Activations Density 0.002%

    No Known Activations