© 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. 27-GEMMASCOPE-2-TRANSCODER-262K
    7. 199070
    Prev
    Next
    INDEX
    Explanations

    `data` class

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_27_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
     pique
    0.41
     interest
    0.38
    Waters
    0.38
    Poll
    0.37
    এদিকে
    0.37
    ])
    0.37
    মা
    0.37
     প্রাপ্ত
    0.36
    wass
    0.36
    珀
    0.35
    POSITIVE LOGITS
     Mereka
    0.52
     mereka
    0.42
     کریم
    0.41
     actriz
    0.39
     Ketika
    0.38
    ഘോഷ
    0.38
     pemimpin
    0.38
     Agosto
    0.38
    ivirus
    0.38
     líder
    0.38
    Activations Density 0.000%

    No Known Activations