© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-TRANSCODER-262K
    7. 165936
    Prev
    Next
    INDEX
    Explanations

    *. **Height & Falling:**" - Period followed by asterisks and a new section. - "circuit. If you are not comfortable working with electricity, *do not attempt this project*. Consider starting with low-voltage," - Period followed by an asterisk and a new section. - "process. Work quickly. * **Sanitation:**" - Period followed by an asterisk and a new section.**Store**

    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_31_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
     jangan
    0.48
     อย่า
    0.46
    อย่า
    0.43
    ாவது
    0.41
     റേ
    0.40
     đừng
    0.39
     হয়নি
    0.38
    柛
    0.38
    勿
    0.37
     έτσι
    0.37
    POSITIVE LOGITS
    亡
    0.40
    Caprio
    0.39
     capitals
    0.38
     menengah
    0.37
    ᄌ
    0.37
    ChooserView
    0.37
    Economic
    0.36
    PPh
    0.35
    рор
    0.35
     madison
    0.35
    Activations Density 0.007%

    No Known Activations