© 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. 195327
    Prev
    Next
    INDEX
    Explanations

    wikimedia

    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
    Typical
    0.40
     Typical
    0.39
    Geo
    0.37
    Kol
    0.36
    ἅ
    0.36
     Difficulty
    0.35
    rup
    0.35
     Kol
    0.35
     Similarity
    0.35
    kn
    0.34
    POSITIVE LOGITS
    ڎ
    0.42
    лях
    0.40
     Conductivity
    0.39
    ・・
    0.38
     coeff
    0.38
     NFL
    0.38
     মিড
    0.38
    vaart
    0.38
    感受
    0.38
     通販
    0.37
    Activations Density 0.000%

    No Known Activations