© 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. 18-GEMMASCOPE-2-TRANSCODER-262K
    7. 88767
    Prev
    Next
    INDEX
    Explanations

    dialogue punctuation and conjunctions

    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_18_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
    ಸ್ಟ್
    0.22
    쥘
    0.22
    anzit
    0.21
     крупней
    0.21
     Gustave
    0.21
    irmer
    0.21
     admissible
    0.20
     épars
    0.20
     კიდ
    0.20
    oration
    0.20
    POSITIVE LOGITS
    Однако
    0.17
    ＞
    0.17
    正面
    0.17
     رضا
    0.17
    反而
    0.17
     Phần
    0.17
    此刻
    0.17
     gia
    0.17
     phát
    0.17
     however
    0.17
    Activations Density 0.002%

    No Known Activations