© 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. 6471
    Prev
    Next
    INDEX
    Explanations

    following punctuation

    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
     Bho
    0.09
    toi
    0.09
    聿
    0.09
     "
    0.08
     Kejriwal
    0.08
    もし
    0.08
     IoT
    0.08
     menuju
    0.08
     Out
    0.08
    hp
    0.08
    POSITIVE LOGITS
     númer
    0.10
     বিস্ফোর
    0.09
     distância
    0.09
     predecess
    0.09
     bảy
    0.09
    ⚐
    0.08
     नियमों
    0.08
    حده
    0.08
     कलम
    0.08
     deviate
    0.08
    Activations Density 0.272%

    No Known Activations