© 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. 77071
    Prev
    Next
    INDEX
    Explanations

    possession

    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
     dumps
    0.38
     Rub
    0.35
    Darwin
    0.35
    ણને
    0.34
    Rub
    0.34
    にあ
    0.34
    triggers
    0.34
    Po
    0.33
    脆
    0.33
    dump
    0.32
    POSITIVE LOGITS
     possessed
    1.92
     possess
    1.80
     possession
    1.77
     possesses
    1.70
    拥有
    1.59
     Possession
    1.58
    擁有
    1.55
     possessing
    1.52
     posiad
    1.48
    possessed
    1.47
    Activations Density 0.001%

    No Known Activations