© 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. 154380
    Prev
    Next
    INDEX
    Explanations

    internet network

    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
     jo
    0.41
     দৃশ্য
    0.40
    Jo
    0.39
     चुन
    0.38
     Jo
    0.37
    䐝
    0.36
    стоя
    0.36
    जोर
    0.36
     Cho
    0.35
     cho
    0.35
    POSITIVE LOGITS
    ֣
    0.40
    wik
    0.40
    ıdır
    0.39
    kwik
    0.38
    ektion
    0.38
     yako
    0.37
    ᡠ
    0.37
    bia
    0.36
    Congrats
    0.36
    ℠
    0.36
    Activations Density 0.000%

    No Known Activations