© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 48582
    Prev
    Next
    INDEX
    Explanations

    was

    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_55_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
     ஸ்ப
    0.45
     Бі
    0.44
     Éd
    0.40
    ﭼ
    0.40
     Ấ
    0.40
     Χ
    0.39
     Им
    0.39
     ई
    0.39
     भरकर
    0.38
     Су
    0.38
    POSITIVE LOGITS
     administra
    0.70
     transforma
    0.69
     alterna
    0.64
     investi
    0.63
     determina
    0.63
     construc
    0.62
     concentra
    0.61
     identifica
    0.60
     educa
    0.60
     break
    0.59
    Activations Density 0.002%

    No Known Activations