© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 200851
    Prev
    Next
    INDEX
    Explanations

    grammatical connectors

    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_50_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
    Nombre
    0.39
     menudo
    0.38
    ધ્ય
    0.38
    ʈ
    0.38
    шком
    0.37
    担
    0.37
    Hop
    0.36
    cimientos
    0.36
     restos
    0.36
    ligen
    0.36
    POSITIVE LOGITS
     furl
    0.42
    FromArray
    0.41
    UniqueID
    0.40
     ایست
    0.39
    ismiss
    0.38
     sr
    0.38
    -{\
    0.38
     furlough
    0.38
    ราย
    0.37
     xay
    0.37
    Activations Density 0.000%

    No Known Activations