© 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. 82714
    Prev
    Next
    INDEX
    Explanations

    instructions and steps

    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
     breed
    0.45
     Elaine
    0.41
    вний
    0.41
    elé
    0.38
    earic
    0.38
    PARTMENT
    0.37
    愭
    0.37
     gerçek
    0.36
     Gä
    0.36
    appid
    0.36
    POSITIVE LOGITS
    </u>
    0.38
    Considering
    0.35
    Us
    0.35
      
    0.34
    ወሰ
    0.34
     minul
    0.34
    .+\
    0.34
    -]+
    0.34
     സൂര്യ
    0.34
     Sora
    0.33
    Activations Density 0.003%

    No Known Activations