© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 26-GEMMASCOPE-2-TRANSCODER-262K
    4. 195892
    Prev
    Next
    INDEX
    Explanations

    object initialization methods

    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_26_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
     destruction
    0.37
    抉
    0.37
    </h3>
    0.35
    entuan
    0.34
     छोटे
    0.33
     disparity
    0.33
     thinning
    0.33
     Destruction
    0.33
    ড়ি
    0.33
     хоче
    0.33
    POSITIVE LOGITS
    that
    0.55
    which
    0.46
     that
    0.43
    ซึ่ง
    0.41
    که
    0.40
    이
    0.39
    Ghana
    0.39
    including
    0.38
    since
    0.38
     aşağıdaki
    0.38
    Activations Density 0.003%

    No Known Activations