© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 207380
    Prev
    Next
    INDEX
    Explanations

    programming code

    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_46_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
     هدف
    0.40
     pretentious
    0.39
     청
    0.39
     orta
    0.39
    칙
    0.38
     тести
    0.37
     misty
    0.37
     intramolecular
    0.37
    Testing
    0.36
    Kle
    0.36
    POSITIVE LOGITS
     টেনে
    0.41
    𝚇
    0.39
     ब्लड
    0.38
    isOpen
    0.38
     Лей
    0.37
    Mall
    0.37
     Engineer
    0.36
     സാധ
    0.36
     Mall
    0.36
     обработки
    0.35
    Activations Density 0.001%

    No Known Activations