© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 54984
    Prev
    Next
    INDEX
    Explanations

    steel

    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_55_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
    ويم
    0.41
    IDGE
    0.40
    悌
    0.39
     Peterson
    0.38
     اقت
    0.38
     मियां
    0.36
    brothers
    0.36
    舔
    0.35
    aitu
    0.35
    premi
    0.34
    POSITIVE LOGITS
     materiales
    0.63
     materials
    0.61
     materiali
    0.59
    材料
    0.57
    materials
    0.54
     matériaux
    0.54
    Materials
    0.52
     materiais
    0.52
     Materials
    0.51
     مواد
    0.51
    Activations Density 0.003%

    No Known Activations