© 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. 137135
    Prev
    Next
    INDEX
    Explanations

    games or systems

    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
    റിന്റെ
    0.48
    ຜ
    0.40
    异
    0.37
    }]$.
    0.37
    Მ
    0.37
    Xs
    0.36
     resol
    0.36
    cris
    0.35
    anak
    0.35
    effet
    0.35
    POSITIVE LOGITS
     Sitting
    0.39
     Tunisian
    0.37
     dió
    0.37
    Tul
    0.37
     ning
    0.36
     kij
    0.36
    ArgsConstructor
    0.36
    nienie
    0.36
    Ту
    0.36
    轍
    0.36
    Activations Density 0.000%

    No Known Activations