© 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. 50-GEMMASCOPE-2-TRANSCODER-262K
    7. 198585
    Prev
    Next
    INDEX
    Explanations

    comfort food

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_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
     माल
    0.47
     मल
    0.44
     BAT
    0.42
     Baltimore
    0.42
    厸
    0.38
     Browns
    0.38
     Tomato
    0.38
     консу
    0.38
     நூற்றாண்டில்
    0.37
    REGIUNE
    0.37
    POSITIVE LOGITS
    Dani
    0.37
     ጥ
    0.36
    fueled
    0.36
    க்கா
    0.36
    asyarakat
    0.35
    শান্ত
    0.35
    汐
    0.35
    جاد
    0.34
     Nara
    0.34
     조합
    0.34
    Activations Density 0.001%

    No Known Activations