© 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. 39-GEMMASCOPE-2-TRANSCODER-262K
    7. 4274
    Prev
    Next
    INDEX
    Explanations

    equal or equality

    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_39_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
     höher
    0.41
    槇
    0.36
    Normalization
    0.36
    
    0.36
     mentors
    0.35
    Bracketing
    0.35
     তিনজন
    0.35
     anisotropic
    0.34
     Validación
    0.34
    
    0.34
    POSITIVE LOGITS
    同
    0.51
    ensureEqual
    0.48
     равно
    0.47
     iguais
    0.46
     đồng
    0.46
     EQU
    0.45
     uguale
    0.45
     equal
    0.44
     equivalente
    0.44
    equivalent
    0.44
    Activations Density 0.159%

    No Known Activations