© 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. 53-GEMMASCOPE-2-TRANSCODER-262K
    7. 77199
    Prev
    Next
    INDEX
    Explanations

    data formats

    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
     inefficient
    0.39
    を送
    0.38
    mah
    0.37
     வயி
    0.36
    栩
    0.36
     حقی
    0.36
     рез
    0.36
    akami
    0.36
    뜯
    0.36
    thunder
    0.36
    POSITIVE LOGITS
     bases
    0.39
     Cl
    0.38
     Kl
    0.37
    Costs
    0.37
     format
    0.37
     Banks
    0.37
     registration
    0.37
    ியுள்ள
    0.36
    MenuItems
    0.36
    Formats
    0.35
    Activations Density 0.001%

    No Known Activations