© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 169108
    Prev
    Next
    INDEX
    Explanations

    Con

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Con
    2.22
     Con
    2.20
     kon
    2.16
     кон
    2.06
    con
    2.03
     con
    1.83
     CON
    1.70
     컨
    1.70
     Kon
    1.62
    CON
    1.59
    POSITIVE LOGITS
     आधिकारिक
    0.42
     officielle
    0.40
     официа
    0.40
     officiel
    0.40
    𝙫
    0.40
     Официа
    0.40
     официально
    0.40
     офі
    0.39
    𝙴
    0.38
    ically
    0.38
    Activations Density 0.001%

    No Known Activations