© 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. 26879
    Prev
    Next
    INDEX
    Explanations

    formation

    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
     Stark
    0.36
     Nxd
    0.35
    ளே
    0.35
    䡓
    0.35
     कार्यकर्
    0.34
    PlistBuddy
    0.34
    Opera
    0.32
    ลม
    0.32
    InstanceOf
    0.32
    術
    0.32
    POSITIVE LOGITS
     formed
    2.89
     forming
    2.67
     formation
    2.66
    形成
    2.55
     Forming
    2.48
    formed
    2.47
     formación
    2.47
     Formation
    2.45
     formação
    2.42
    Formation
    2.39
    Activations Density 0.061%

    No Known Activations