© 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
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 198231
    Prev
    Next
    INDEX
    Explanations

    technical terms

    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
     تعدى
    0.46
    लिये
    0.43
     Kran
    0.42
    骄
    0.42
     Fashion
    0.41
     Accident
    0.40
    ⃝
    0.39
     Structural
    0.39
    條件
    0.39
     Conting
    0.39
    POSITIVE LOGITS
    ථා
    0.39
    zf
    0.37
     neun
    0.37
     `"
    0.35
    的最
    0.35
     drumming
    0.35
    ր
    0.35
    ửa
    0.34
     applying
    0.34
     interviewing
    0.33
    Activations Density 0.001%

    No Known Activations