© 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. 40-GEMMASCOPE-2-TRANSCODER-262K
    7. 192
    Prev
    Next
    INDEX
    Explanations

    beverages

    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_40_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
     যান
    0.42
    aciju
    0.40
    urança
    0.40
    屁
    0.39
     Geträn
    0.38
     напи
    0.37
     anb
    0.37
    蜓
    0.37
    <0xA2>
    0.37
    omen
    0.37
    POSITIVE LOGITS
     wine
    0.76
     tea
    0.73
     beer
    0.72
    Wine
    0.72
    wine
    0.70
     water
    0.68
     Wine
    0.68
    Tea
    0.66
     Beer
    0.65
    茶
    0.65
    Activations Density 0.070%

    No Known Activations