© 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. 33612
    Prev
    Next
    INDEX
    Explanations

    relationship with your

    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
    本
    0.47
    本の
    0.41
    hbase
    0.41
     अधिक
    0.38
     geographic
    0.36
    oble
    0.36
    地理
    0.36
    maan
    0.36
     சிகி
    0.35
    wci
    0.35
    POSITIVE LOGITS
     මිල
    0.40
     వారు
    0.39
    〃
    0.36
     Anthrop
    0.35
    嘰
    0.35
     فروش
    0.34
     fullest
    0.34
     inanimate
    0.34
     소비
    0.34
     ‘
    0.34
    Activations Density 0.004%

    No Known Activations