© 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
    3. Gemma-3-27B-IT
    5. 56-GEMMASCOPE-2-TRANSCODER-262K
    7. 21448
    Prev
    Next
    INDEX
    Explanations

    abstract

    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_56_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
     écrire
    0.43
    लेख
    0.38
     writing
    0.38
     пишу
    0.38
    寫
    0.38
     เขียน
    0.37
    Writing
    0.37
     escrita
    0.37
    写
    0.37
     viết
    0.36
    POSITIVE LOGITS
     für
    0.39
     voor
    0.39
     for
    0.39
    ад
    0.38
     gesagt
    0.36
    rubber
    0.36
    ogram
    0.36
    please
    0.36
    clause
    0.36
     Please
    0.36
    Activations Density 0.001%

    No Known Activations