© 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. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 66562
    Prev
    Next
    INDEX
    Explanations

    instant ramen noodles

    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_41_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
    Rocky
    0.40
    reonine
    0.39
     ธ
    0.38
     ቀ
    0.37
     Rocky
    0.36
    asionally
    0.36
    휋
    0.36
    耆
    0.35
    uscular
    0.35
     Amber
    0.35
    POSITIVE LOGITS
     ramen
    1.23
     noodles
    1.10
     noodle
    1.10
     Ramen
    1.05
     Noodles
    1.02
    noodles
    0.96
     instant
    0.93
    ラーメン
    0.89
     Instant
    0.87
    🍜
    0.84
    Activations Density 0.003%

    No Known Activations