© 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. 156810
    Prev
    Next
    INDEX
    Explanations

    0

    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
    gow
    0.39
    ificates
    0.39
    asts
    0.38
    hesion
    0.37
    柏
    0.37
    oster
    0.36
    ure
    0.36
    eron
    0.35
    ulture
    0.35
    sure
    0.35
    POSITIVE LOGITS
     FV
    0.38
     FM
    0.38
     फ़
    0.37
     TM
    0.35
     FG
    0.35
     দুজন
    0.35
     সম্মুখীন
    0.35
     फ़
    0.35
    तलब
    0.35
     藤
    0.35
    Activations Density 0.001%

    No Known Activations