© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 141166
    Prev
    Next
    INDEX
    Explanations

    decide

    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_46_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
    encoded
    0.38
     डी
    0.37
     encoded
    0.37
     coche
    0.37
    我们也
    0.36
     વિશે
    0.36
     comes
    0.36
     ঔ
    0.35
     we
    0.35
    来了
    0.35
    POSITIVE LOGITS
     decide
    1.00
     decided
    0.96
     deciding
    0.95
    决定
    0.91
     Decide
    0.86
    決定
    0.86
     decides
    0.86
     odlu
    0.82
     decid
    0.80
     deciso
    0.80
    Activations Density 0.001%

    No Known Activations