© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 194824
    Prev
    Next
    INDEX
    Explanations

    names and acronyms

    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_50_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
    mRNA
    0.42
     mRNA
    0.39
     helm
    0.38
     তরুণ
    0.36
     rRNA
    0.35
     رکن
    0.35
     ନ
    0.35
     ऑ
    0.35
     Tanner
    0.35
     Helm
    0.34
    POSITIVE LOGITS
    Ocean
    0.45
    ocean
    0.40
    plating
    0.40
    vo
    0.39
    かが
    0.39
     Ocean
    0.39
    ประส
    0.38
     Lido
    0.38
     Gianni
    0.38
    வாய்
    0.38
    Activations Density 0.000%

    No Known Activations