© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 46-GEMMASCOPE-2-TRANSCODER-262K
    4. 66092
    Prev
    Next
    INDEX
    Explanations

    salty dried 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_46_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
     पाये
    0.40
     stern
    0.37
    સર
    0.36
     النظام
    0.36
     intrat
    0.35
    ccionar
    0.35
    ۪
    0.35
     Система
    0.35
     안
    0.35
     ভগ
    0.34
    POSITIVE LOGITS
     salted
    1.07
    salted
    0.91
     salt
    0.90
     Salt
    0.89
     dried
    0.86
    Salt
    0.86
    salt
    0.81
     smoked
    0.81
    塩
    0.78
     salty
    0.76
    Activations Density 0.039%

    No Known Activations