© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143600
    Prev
    Next
    INDEX
    Explanations

    PATH

    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
    Negative Logits
     wrong
    0.45
     शान
    0.38
     propriet
    0.37
     efficiency
    0.37
    host
    0.36
    муще
    0.35
     neutral
    0.34
    Efficiency
    0.34
    سكري
    0.34
    旗
    0.34
    POSITIVE LOGITS
    Checker
    0.42
    IBLE
    0.39
    berat
    0.37
     গন
    0.37
     আবদ্ধ
    0.36
     буквы
    0.36
    แน่น
    0.36
    検査
    0.35
     চাপের
    0.35
     synaptic
    0.35
    Activations Density 0.001%

    No Known Activations