© 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. 23-GEMMASCOPE-2-TRANSCODER-262K
    4. 86918
    Prev
    Next
    INDEX
    Explanations

    **tablespoons of ingredients or ABV percentage**

    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_23_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
    IBAction
    0.17
    []{
    0.17
    Vert
    0.16
    			
    0.16
    NASA
    0.15
    三十
    0.15
    鎴
    0.15
     తెలిసి
    0.15
    批量
    0.15
    夜
    0.14
    POSITIVE LOGITS
     pulau
    0.18
     lì
    0.18
     korrekt
    0.18
     ratt
    0.18
     lily
    0.17
     lö
    0.17
     europe
    0.16
     Orchid
    0.16
     cooperación
    0.16
     islets
    0.16
    Activations Density 0.004%

    No Known Activations