© 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. 13-GEMMASCOPE-2-TRANSCODER-262K
    7. 14417
    Prev
    Next
    INDEX
    Explanations

    spicy heat peppers

    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_13_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
     पवन
    0.40
    ნ
    0.39
     renormal
    0.35
    ক
    0.35
    პ
    0.34
     komun
    0.33
    పోయ
    0.32
    ν
    0.32
     hugely
    0.32
     उपाध्यक्ष
    0.32
    POSITIVE LOGITS
     peppers
    0.43
    辣椒
    0.41
     chili
    0.40
    🌶
    0.38
    辣
    0.37
     disposit
    0.35
     allClasses
    0.35
     मिरची
    0.35
    اة
    0.33
     fina
    0.33
    Activations Density 0.086%

    No Known Activations