© 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. 37-GEMMASCOPE-2-TRANSCODER-262K
    7. 133721
    Prev
    Next
    INDEX
    Explanations

    door, doors, opening, hinges

    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_37_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
     руки
    0.40
     pearson
    0.38
     sentence
    0.37
     daisy
    0.37
     apont
    0.37
    劧
    0.37
     Rana
    0.37
    Kyle
    0.37
    μοι
    0.36
    Pearson
    0.36
    POSITIVE LOGITS
     door
    1.02
     Door
    0.99
     двер
    0.93
    door
    0.89
     DOOR
    0.88
     doors
    0.87
    Door
    0.87
     дверь
    0.83
     Doors
    0.82
    门
    0.81
    Activations Density 0.002%

    No Known Activations