© 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. 24-GEMMASCOPE-2-TRANSCODER-262K
    7. 177877
    Prev
    Next
    INDEX
    Explanations

    rating scale 1-5

    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_24_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
     ذمہ
    0.41
    サリー
    0.39
     diminue
    0.39
     возможностей
    0.39
     wzrost
    0.39
     vorher
    0.38
    पीड़
    0.38
    寵
    0.38
     autocor
    0.38
    خود
    0.37
    POSITIVE LOGITS
    ams
    0.40
    ugawa
    0.39
    isyon
    0.38
    ated
    0.38
    wia
    0.38
    ama
    0.37
    esi
    0.37
    ayas
    0.37
     probably
    0.37
    ulu
    0.37
    Activations Density 0.004%

    No Known Activations