© 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. 38-GEMMASCOPE-2-TRANSCODER-262K
    7. 3923
    Prev
    Next
    INDEX
    Explanations

    arithmetic operators and numbers

    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_38_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
     Ruler
    0.41
    ikal
    0.37
     тыся
    0.36
     Kral
    0.36
    OnError
    0.36
    ambilan
    0.36
     千
    0.35
     körper
    0.35
     Mother
    0.35
     Quick
    0.34
    POSITIVE LOGITS
    PrototypeOf
    0.45
     এক্সপ্রেস
    0.41
     einige
    0.39
     خوات
    0.39
    Intent
    0.37
    zinc
    0.37
    वीं
    0.37
     aunts
    0.35
    ungsl
    0.35
    듀
    0.35
    Activations Density 0.151%

    No Known Activations