© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 67359
    Prev
    Next
    INDEX
    Explanations

    drug, compound, molecule

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_46_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
     Property
    0.45
    씰
    0.45
     Properties
    0.44
     properties
    0.43
     albi
    0.42
    property
    0.41
     propiedades
    0.41
     प्रॉपर्टी
    0.41
     property
    0.41
     propriedades
    0.41
    POSITIVE LOGITS
    testX
    0.39
    ^+$
    0.38
    אן
    0.37
    PAN
    0.37
    явля
    0.36
    Pan
    0.36
     SCRE
    0.36
    Roger
    0.36
    愁
    0.36
     series
    0.35
    Activations Density 0.003%

    No Known Activations