© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 242878
    Prev
    Next
    INDEX
    Explanations

    Perplexity AI

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_40_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
    operations
    0.37
    <0xAD>
    0.37
    Sally
    0.37
     салу
    0.37
    istica
    0.36
     кампа
    0.36
    version
    0.36
     Industries
    0.36
    塭
    0.36
     سج
    0.36
    POSITIVE LOGITS
    لاص
    0.38
    HomeController
    0.38
    试
    0.37
     मर्
    0.37
    льнявыя
    0.36
     grazing
    0.36
     인터넷
    0.36
     mencionar
    0.35
     zil
    0.35
     muc
    0.34
    Activations Density 0.001%

    No Known Activations