© 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. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 35980
    Prev
    Next
    INDEX
    Explanations

    multilingual context indicators

    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_11_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
    en
    0.66
     Lein
    0.63
     Suède
    0.63
    و
    0.60
    ান
    0.58
    的态度
    0.57
    াহ
    0.57
     ਵਿੱਚ
    0.55
    യുള്ള
    0.55
     മറ്റു
    0.54
    POSITIVE LOGITS
    मिताभ
    0.58
     occasione
    0.55
    ﻑ
    0.55
    ТУ
    0.52
    点が
    0.51
    các
    0.51
    ﺏ
    0.50
     qualche
    0.50
    Walmart
    0.49
    PH
    0.49
    Activations Density 0.001%

    No Known Activations