© 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
    2. Gemma-3-27B-IT
    3. 47-GEMMASCOPE-2-TRANSCODER-262K
    4. 216753
    Prev
    Next
    INDEX
    Explanations

    optimal

    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_47_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
    Stability
    0.44
     Stability
    0.43
     うん
    0.40
    オーダー
    0.39
    fromUtf
    0.38
     stabilité
    0.38
    OrderItem
    0.37
     갈
    0.37
    বারি
    0.36
     pushedAt
    0.36
    POSITIVE LOGITS
     optimal
    0.51
    Optimal
    0.44
    optimal
    0.43
     Optimal
    0.42
     stochastic
    0.40
     cushions
    0.40
     optimum
    0.39
     CAV
    0.39
     प्लास्टिक
    0.39
    div
    0.39
    Activations Density 0.004%

    No Known Activations