© 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. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 20708
    Prev
    Next
    INDEX
    Explanations

    beginnings

    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_56_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
     j
    0.61
     t
    0.58
     v
    0.54
     т
    0.54
     declines
    0.48
     declined
    0.46
     declining
    0.45
     decline
    0.45
     first
    0.44
     ج
    0.44
    POSITIVE LOGITS
    摑
    0.39
    Along
    0.38
    迂
    0.37
    Timing
    0.36
    㗊
    0.36
    atern
    0.35
    Exper
    0.35
    做一个
    0.35
    timing
    0.34
    setDefault
    0.33
    Activations Density 0.010%

    No Known Activations