© 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. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 81166
    Prev
    Next
    INDEX
    Explanations

    component event assignments

    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_31_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
     pretends
    0.42
     fulfils
    0.41
     เพื่อ
    0.41
    বিবি
    0.39
     upang
    0.38
    ṓ
    0.38
    スマ
    0.38
     उर्दू
    0.38
     szól
    0.38
     промы
    0.37
    POSITIVE LOGITS
     Cantor
    0.41
    Cant
    0.38
    콥
    0.37
     Cant
    0.37
    astrophe
    0.37
    नीकरण
    0.36
     Rose
    0.36
    equivalent
    0.36
     Bronze
    0.36
     Initiate
    0.36
    Activations Density 0.000%

    No Known Activations