© 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. 176576
    Prev
    Next
    INDEX
    Explanations

    pick

    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
    ças
    0.47
    ʂ
    0.43
     કરવું
    0.42
    ureshi
    0.42
    xtures
    0.40
    াইলেন
    0.39
     السابع
    0.39
    ça
    0.39
    ޞ
    0.38
     ಮಾಡಲು
    0.38
    POSITIVE LOGITS
    bier
    0.39
     head
    0.38
    となります
    0.38
     yal
    0.38
    ique
    0.37
     приста
    0.37
    放
    0.37
    head
    0.36
    BSP
    0.36
    バラ
    0.36
    Activations Density 0.001%

    No Known Activations