© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 12306
    Prev
    Next
    INDEX
    Explanations

    `https://` links and image links

    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
     telegram
    0.42
     Telegram
    0.42
    㖡
    0.42
     Blogger
    0.41
     huyết
    0.40
    telegram
    0.39
     watts
    0.38
    ☟
    0.38
    ুদ্র
    0.38
     سرکاری
    0.38
    POSITIVE LOGITS
    Star
    0.44
     نج
    0.40
     Star
    0.39
    نج
    0.39
     emanc
    0.38
     violations
    0.37
     electronics
    0.37
     CIO
    0.37
    STAR
    0.37
    шни
    0.36
    Activations Density 0.002%

    No Known Activations