© 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. 10-GEMMASCOPE-2-TRANSCODER-262K
    7. 25552
    Prev
    Next
    INDEX
    Explanations

    Indian food dishes and sauces

    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_10_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
    ूं
    0.25
    通过
    0.24
     продаже
    0.24
    ირ
    0.23
    出
    0.23
    甴
    0.23
    Ｙ
    0.23
     люди
    0.23
    想
    0.23
    बा
    0.23
    POSITIVE LOGITS
     wouldnt
    0.28
     teria
    0.24
     couldnt
    0.24
     দ্য
    0.24
    adamia
    0.22
     reacts
    0.22
     ähm
    0.22
     januari
    0.22
     meriye
    0.22
    activate
    0.22
    Activations Density 0.051%

    No Known Activations