© 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. 76848
    Prev
    Next
    INDEX
    Explanations

    D names

    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
    /(:
    0.38
    Ῥ
    0.38
    郅
    0.38
    aktur
    0.38
    ঙ্কা
    0.38
     replying
    0.37
    琍
    0.37
     H
    0.37
     rayos
    0.36
     தெரிவித்த
    0.36
    POSITIVE LOGITS
     VAN
    0.46
     Vân
    0.43
    Van
    0.40
    LING
    0.40
     وصحبه
    0.39
    слов
    0.38
    VAN
    0.38
    stück
    0.37
    滕
    0.37
     Van
    0.37
    Activations Density 0.000%

    No Known Activations