© 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. 156992
    Prev
    Next
    INDEX
    Explanations

    red and green

    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
     दू
    0.39
     قوان
    0.38
    ={[
    0.38
    наў
    0.38
     Gerade
    0.37
     स्ट्रेट
    0.36
     ರೀ
    0.36
    #__
    0.36
    Sergio
    0.36
     keyDown
    0.36
    POSITIVE LOGITS
    topping
    0.42
     unrest
    0.42
     요
    0.42
     potato
    0.38
    ës
    0.38
    Carl
    0.38
    Athena
    0.38
    BLINK
    0.37
     കലാ
    0.37
    XB
    0.37
    Activations Density 0.000%

    No Known Activations