© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-TRANSCODER-262K
    7. 65549
    Prev
    Next
    INDEX
    Explanations

    bouillon cubes and stock

    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
    getBean
    0.42
    řad
    0.41
    掠
    0.41
     Terminal
    0.41
     शिका
    0.41
    τικ
    0.38
     fontSize
    0.38
    ự
    0.38
    andfeel
    0.37
     Cic
    0.37
    POSITIVE LOGITS
     bouillon
    1.00
     cube
    0.85
     Bou
    0.74
     bullion
    0.73
     bou
    0.71
     cubes
    0.69
    Bou
    0.69
    cube
    0.68
     broth
    0.68
    Cube
    0.67
    Activations Density 0.013%

    No Known Activations