© 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. 20-GEMMASCOPE-2-TRANSCODER-262K
    7. 211904
    Prev
    Next
    INDEX
    Explanations

    same creator of teams

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_20_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
    வ்வா
    0.40
     cabling
    0.39
    ຕົ
    0.39
     dateTime
    0.38
    셰
    0.38
    vehicles
    0.38
    鸩
    0.38
     tls
    0.37
    ങ്ങളിലും
    0.37
    ittura
    0.37
    POSITIVE LOGITS
    Cols
    0.45
     Kut
    0.44
     Cols
    0.44
    Returning
    0.41
    ressen
    0.40
     bowiem
    0.39
    Kon
    0.39
    Behind
    0.39
    張
    0.39
     karde
    0.39
    Activations Density 0.014%

    No Known Activations