© 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
    3. Gemma-3-27B-IT
    5. 1-GEMMASCOPE-2-TRANSCODER-262K
    7. 132240
    Prev
    Next
    INDEX
    Explanations

    food carts, food court, food snack

    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_1_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
    ف
    1.73
    ו
    1.63
    ש
    1.45
    is
    1.43
    م
    1.41
    س
    1.40
    ח
    1.38
    т
    1.38
    os
    1.36
    li
    1.34
    POSITIVE LOGITS
     sanit
    0.99
     categor
    0.87
     bestowed
    0.87
     complication
    0.87
     oxid
    0.86
     de
    0.86
    ín
    0.84
     correctional
    0.83
    中
    0.81
    乗
    0.81
    Activations Density 0.003%

    No Known Activations