© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 143347
    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
     remember
    0.54
    remember
    0.49
     Remember
    0.45
    覚え
    0.41
     {}\
    0.40
    Remember
    0.38
    记住
    0.37
     remembered
    0.37
     याद
    0.37
     пам
    0.36
    POSITIVE LOGITS
    ទ្ធ
    0.42
     kann
    0.37
     sekali
    0.37
    halo
    0.37
    ोरेशन
    0.37
     ના
    0.36
    মাত্রা
    0.36
    handel
    0.36
    芊
    0.36
    বায়
    0.35
    Activations Density 0.001%

    No Known Activations