© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 59-GEMMASCOPE-2-TRANSCODER-262K
    7. 149132
    Prev
    Next
    INDEX
    Explanations

    know rules skills

    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_59_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
    的话
    0.39
    ücht
    0.38
    的話
    0.38
    Text
    0.36
    esus
    0.35
    ("--
    0.35
    রাস
    0.34
     Buss
    0.34
    exams
    0.34
    drugs
    0.34
    POSITIVE LOGITS
    淉
    0.42
    ちに
    0.39
     обраща
    0.37
     Aur
    0.36
     Cyclic
    0.36
     Feeding
    0.35
    ູນ
    0.35
     obnoxious
    0.35
    ratie
    0.35
     meditate
    0.34
    Activations Density 0.001%

    No Known Activations