© 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. 46-GEMMASCOPE-2-TRANSCODER-262K
    7. 195801
    Prev
    Next
    INDEX
    Explanations

    light

    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
     light
    0.52
    光
    0.51
     свет
    0.48
     Light
    0.47
     ánh
    0.47
     lumière
    0.45
     dark
    0.44
     प्रकाश
    0.44
     光
    0.43
    licht
    0.41
    POSITIVE LOGITS
     relentlessly
    0.40
    寶寶
    0.39
    izal
    0.38
     श्रद्धाल
    0.38
    통산
    0.37
     بى
    0.37
    घर
    0.36
     হইয়াছে
    0.36
    preneur
    0.36
     স্বীক
    0.36
    Activations Density 0.004%

    No Known Activations