© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 214872
    Prev
    Next
    INDEX
    Explanations

    Carl Jung, Paul Klee

    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
    Not in Any Lists

    No Comments

    Negative Logits
     de
    0.40
     Fairchild
    0.39
    hern
    0.39
    D
    0.38
     أل
    0.38
     Zy
    0.37
    ync
    0.37
     D
    0.37
    कर्षण
    0.37
    Dur
    0.36
    POSITIVE LOGITS
    टू
    0.41
     KNO
    0.40
     musik
    0.39
     EFT
    0.39
    নীতি
    0.39
     последнее
    0.38
     विकल्पों
    0.38
     क्रिएट
    0.38
     Конститу
    0.38
    गू
    0.38
    Activations Density 0.001%

    No Known Activations