© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 199735
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
     perhatian
    0.42
     dealt
    0.39
    扎
    0.39
    護
    0.39
    Attention
    0.38
    留意
    0.37
    护
    0.37
    ាំង
    0.36
    lenme
    0.36
     atenção
    0.36
    POSITIVE LOGITS
     Metast
    0.42
     dinheiro
    0.39
     Coatings
    0.39
     Decision
    0.38
     Croft
    0.38
     मित्त
    0.37
     money
    0.37
     LIMIT
    0.37
     typical
    0.36
    밋
    0.36
    Activations Density 0.001%

    No Known Activations