© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 10540
    Prev
    Next
    INDEX
    Explanations

    explaining in simple terms

    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
    Negative Logits
     Inheritance
    0.40
     एडवांस
    0.38
     Recipes
    0.36
     recesses
    0.36
     Diverse
    0.36
     Fernanda
    0.35
     FRENCH
    0.35
     MERCHANTABILITY
    0.34
     Showcase
    0.34
    堊
    0.34
    POSITIVE LOGITS
    omét
    0.37
    ь
    0.36
     ratio
    0.36
    _{(
    0.36
    yak
    0.35
    ्या
    0.35
    ជាមួយ
    0.34
    ニン
    0.34
    ilent
    0.34
     shy
    0.34
    Activations Density 0.005%

    No Known Activations