© 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. 34-GEMMASCOPE-2-TRANSCODER-262K
    7. 167526
    Prev
    Next
    INDEX
    Explanations

    dialogue markers, user requests

    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_34_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
     škola
    0.38
    唃
    0.36
     ဆို
    0.35
     biên
    0.34
     Pak
    0.34
     etik
    0.34
    桿
    0.34
    水印
    0.33
    ޒ
    0.33
     Verz
    0.33
    POSITIVE LOGITS
    推出了
    0.38
    Monday
    0.38
     unquestionably
    0.37
    给予
    0.37
    December
    0.37
     நடைபெற்ற
    0.36
     December
    0.35
    £
    0.35
    因为
    0.35
     Потому
    0.35
    Activations Density 0.001%

    No Known Activations