© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 11-GEMMASCOPE-2-TRANSCODER-262K
    7. 90032
    Prev
    Next
    INDEX
    Explanations

    food and drink pairings

    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_11_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
     మద్యం
    0.63
     తాగ
    0.61
     ..$
    0.61
     алкого
    0.61
     మద్య
    0.61
     ሙሉ
    0.61
    alcool
    0.60
    কী
    0.59
     ))}
    0.58
     Необходимо
    0.58
    POSITIVE LOGITS
     resource
    0.54
    м
    0.50
    бия
    0.50
    мом
    0.50
    $\
    0.49
    ンの
    0.49
    0
    0.47
    斯
    0.46
     bystand
    0.46
     barrio
    0.46
    Activations Density 0.005%

    No Known Activations