© 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. 4180
    Prev
    Next
    INDEX
    Explanations

    date format

    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
     ব্য
    0.38
     থাকলে
    0.37
    ব্য
    0.36
    oree
    0.36
    ໜ
    0.36
    ፊት
    0.35
    ेबल
    0.34
     Wsp
    0.34
     যুদ্ধের
    0.34
    ermen
    0.34
    POSITIVE LOGITS
     fuck
    0.42
     shit
    0.40
     gimana
    0.39
     fucking
    0.39
     PTS
    0.38
     skillfully
    0.38
     그러면은
    0.38
    畀
    0.38
     XXIII
    0.38
    PTI
    0.38
    Activations Density 0.176%

    No Known Activations