© 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. 30-GEMMASCOPE-2-TRANSCODER-262K
    7. 52376
    Prev
    Next
    INDEX
    Explanations

    original / former

    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_30_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
    context
    0.35
     নজর
    0.35
     Cpu
    0.34
     BatchNorm
    0.34
    FAULT
    0.33
    েন্স
    0.33
    뤄
    0.33
    Ｗ
    0.33
    aggable
    0.33
    ல
    0.33
    POSITIVE LOGITS
    原来的
    0.97
     původ
    0.96
     originally
    0.95
     formerly
    0.91
     ursprünglich
    0.88
     former
    0.87
     original
    0.84
     원래
    0.83
    Originally
    0.82
     ursprüng
    0.81
    Activations Density 0.043%

    No Known Activations