© 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. 233452
    Prev
    Next
    INDEX
    Explanations

    multilingual text

    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
     YOU
    0.38
    YOU
    0.38
    ﺒ
    0.37
    wrote
    0.36
     консульта
    0.36
    らない
    0.35
    ترف
    0.35
    ຄ
    0.35
    плуа
    0.35
    Leftrightarrow
    0.35
    POSITIVE LOGITS
     கிடைத்த
    0.43
    chanted
    0.41
     there
    0.38
    there
    0.38
     ہمیں
    0.38
     допо
    0.37
     разно
    0.37
    annabin
    0.37
    chine
    0.37
     insinu
    0.36
    Activations Density 0.001%

    No Known Activations