© 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. 158494
    Prev
    Next
    INDEX
    Explanations

    chemical names

    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
    Print
    0.40
    ('/:
    0.39
    seagreen
    0.38
     Into
    0.37
    printed
    0.37
    isSelected
    0.37
     ale
    0.37
    ➣
    0.37
     रो
    0.36
    Streak
    0.36
    POSITIVE LOGITS
     Sark
    0.54
    zar
    0.50
     sark
    0.46
     zar
    0.45
    馇
    0.41
    غير
    0.41
    ardu
    0.41
     тура
    0.41
     bap
    0.41
    irim
    0.41
    Activations Density 0.001%

    No Known Activations