© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 29887
    Prev
    Next
    INDEX
    Explanations

    greentext stories

    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_40_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
    Worker
    0.38
     trib
    0.38
     باند
    0.37
     forums
    0.36
     klub
    0.36
    Trib
    0.35
    ᱜ
    0.35
     soldier
    0.35
     forum
    0.35
     хоккей
    0.35
    POSITIVE LOGITS
     Shak
    0.38
    '.$
    0.35
     Innovative
    0.35
    ⎝
    0.35
    出一个
    0.35
    笔
    0.35
    मॉन
    0.33
    profiss
    0.33
     Than
    0.33
     Penang
    0.33
    Activations Density 0.005%

    No Known Activations