© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 59233
    Prev
    Next
    INDEX
    Explanations

    good or evil

    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_11_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
    ia
    0.63
     ricordo
    0.62
     кілько
    0.58
     courtship
    0.57
     nell
    0.56
     máu
    0.55
     CRO
    0.55
    ú
    0.55
     Netflix
    0.54
    的三
    0.52
    POSITIVE LOGITS
    hmen
    0.62
    Pros
    0.61
    シャル
    0.60
    П
    0.60
    ジェル
    0.59
    Зна
    0.59
    bė
    0.59
    С
    0.59
    PHP
    0.58
    u
    0.58
    Activations Density 0.000%

    No Known Activations