© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 1281
    Prev
    Next
    INDEX
    Explanations

    xmlns="http://www.w3.org/2000/svg">

    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_40_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
     تر
    0.42
    钟
    0.42
    imbledon
    0.39
    ديد
    0.38
    ָד
    0.38
    鍾
    0.38
     abandoning
    0.38
    鐘
    0.38
     Aachen
    0.37
    achute
    0.37
    POSITIVE LOGITS
    .[/
    0.39
    线性
    0.38
    زش
    0.37
    тый
    0.36
     liné
    0.36
     linear
    0.35
     linearly
    0.35
    islang
    0.35
     gastric
    0.34
    Bola
    0.34
    Activations Density 0.000%

    No Known Activations