© 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. 47-GEMMASCOPE-2-TRANSCODER-262K
    7. 217673
    Prev
    Next
    INDEX
    Explanations

    non-English web content

    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_47_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
    协
    0.46
     сан
    0.42
    ふ
    0.40
     سان
    0.39
     Ties
    0.39
     لط
    0.38
     صحت
    0.37
     Sanit
    0.37
     গা
    0.37
     Scrub
    0.37
    POSITIVE LOGITS
    šao
    0.41
    潴
    0.40
    tog
    0.39
     tokom
    0.39
    conflict
    0.39
    popupBackground
    0.38
    XII
    0.38
    ঞ্জের
    0.37
     ROG
    0.37
     koliko
    0.37
    Activations Density 0.000%

    No Known Activations