© 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. 55-GEMMASCOPE-2-TRANSCODER-262K
    7. 52194
    Prev
    Next
    INDEX
    Explanations

    Chinese general concepts

    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_55_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
    归
    0.47
    散
    0.45
    விட்டு
    0.44
    歸
    0.43
    会将
    0.42
     消
    0.41
     排
    0.40
     eil
    0.40
    规
    0.40
    規
    0.40
    POSITIVE LOGITS
    可用
    0.42
     ते
    0.38
     முக்கிய
    0.38
     تمامی
    0.37
    يش
    0.36
    Visualization
    0.36
     avoidable
    0.36
    ట
    0.36
    нию
    0.35
    charging
    0.35
    Activations Density 0.004%

    No Known Activations