© 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. 60-GEMMASCOPE-2-TRANSCODER-262K
    7. 151674
    Prev
    Next
    INDEX
    Explanations

    mixed languages and concepts

    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_60_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
     com
    0.50
     l
    0.48
    Com
    0.48
     COM
    0.44
     kom
    0.42
    WERS
    0.42
    ROIT
    0.40
    COM
    0.40
     Com
    0.38
    gins
    0.38
    POSITIVE LOGITS
     À
    0.43
     à
    0.39
     μέ
    0.38
    ̀
    0.37
    àu
    0.37
     dan
    0.37
     Mone
    0.37
     la
    0.36
    ढ़ी
    0.36
    ò
    0.35
    Activations Density 0.003%

    No Known Activations