© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 82455
    Prev
    Next
    INDEX
    Explanations

    academic names

    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_53_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    তুই
    0.47
     ಅಭಿ
    0.37
     फ
    0.37
     Harlan
    0.36
    gallery
    0.36
     благоприят
    0.36
    కర
    0.36
     సహ
    0.36
    ✲
    0.35
    Brush
    0.35
    POSITIVE LOGITS
     inodes
    0.41
    decimals
    0.37
    പ്പിക്കുന്ന
    0.37
    èses
    0.36
     Huz
    0.36
    istiques
    0.36
    usize
    0.36
    ওলানা
    0.35
    inodes
    0.35
    岑
    0.34
    Activations Density 0.001%

    No Known Activations