© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 171113
    Prev
    Next
    INDEX
    Explanations

    opening parenthesis

    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_56_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
     cant
    0.43
     directamente
    0.41
     डायरेक्टली
    0.41
     arent
    0.40
     Directly
    0.40
     dont
    0.39
    Ⴌ
    0.38
    directly
    0.38
     diretamente
    0.37
    +}$,
    0.37
    POSITIVE LOGITS
     General
    0.52
    General
    0.49
     general
    0.46
    BITS
    0.43
     должны
    0.42
     должен
    0.42
     উচিত
    0.41
     considers
    0.40
     Genel
    0.39
    way
    0.39
    Activations Density 0.006%

    No Known Activations