© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 140173
    Prev
    Next
    INDEX
    Explanations

    Game

    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_46_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
     rê
    0.40
    ⑵
    0.40
    ={()
    0.39
    ZW
    0.39
    zovaniyu
    0.39
    بعا
    0.38
    zew
    0.38
     پسند
    0.38
     लाइफ
    0.38
    ⑴
    0.38
    POSITIVE LOGITS
    Speaking
    0.39
     Speaking
    0.36
     Myrtle
    0.35
     blackberry
    0.35
    精准
    0.35
     speaking
    0.34
     challenging
    0.34
    让自己
    0.34
    bleday
    0.34
     infallible
    0.34
    Activations Density 0.000%

    No Known Activations