© 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. 197386
    Prev
    Next
    INDEX
    Explanations

    general concepts and 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
    chomp
    0.40
    tik
    0.40
     locali
    0.40
    大小
    0.39
    ได
    0.39
     bil
    0.38
    ادی
    0.37
    腹
    0.36
    โต
    0.35
     amare
    0.35
    POSITIVE LOGITS
    ્ય
    0.42
     N
    0.41
    ᐳ
    0.40
     Push
    0.40
     расход
    0.40
    ─────
    0.40
     নির্ধারিত
    0.39
     NavigationView
    0.38
    ్యాన్ని
    0.38
    Blueprint
    0.38
    Activations Density 0.016%

    No Known Activations